GINS: A Global intensifier-based N-Gram sentiment dictionary

Abstract

Words are one of the most essential elements of expressing sentiments in context although they are not the only ones. Also, syntactic relationships between words, morphology, punctuation, and linguistic phenomena are influential. Merely considering the concept of words as isolated phenomena causes a lot of mistakes in sentiment analysis systems. So far, a large amount of research has been conducted on generating sentiment dictionaries containing only sentiment words. A number of these dictionaries have addressed the role of combinations of sentiment words, negators, and intensifiers, while almost none of them considered the heterogeneous effect of the occurrence of multiple linguistic phenomena in sentiment compounds. Regarding the weaknesses of the existing sentiment dictionaries, in addressing the heterogeneous effect of the occurrence of multiple intensifiers, this research presents a sentiment dictionary based on the analysis of sentiment compounds including sentiment words, negators, and intensifiers by considering the multiple intensifiers relative to the sentiment word and assigning a location-based coefficient to the intensifier, which increases the covered sentiment phrase in the dictionary, and enhanced efficiency of proposed dictionary-based sentiment analysis methods up to 7% compared to the latest methods.

Keywords

Sentiment analysis sentiment dictionary linguistic phenomena intensifier intensifier location

1 Introduction

The history of modern sentiment analysis dates back to the mid-2000, with the increase of online resources and social media [57]. The importance of sentiment analysis has become more apparent by the introduction of web 2.0 enabling users to express their views on a variety of topics through methods such as consumer forums, social media, and e-governance.

Regarding the enormous amount of information available in today’s world, which has made human and manual analysis almost impossible, in addition to the effect of human opinions in many decisions [70], the importance of sentiment analysis processes by machine-based approaches is increasing.

The various applications of intelligent sentiment recognition and analysis are observable in a wide variety of areas such as cinema and film criticism [19, 73], assessment teaching quality [6 , 94], business and product feedback [7, 59], e-learning [22, 80], and hospitality management and tourism [2, 50]. In the commercial domain, identifying the polarity and orientation of the ideas offered by users helps manufacturers, how to enhance quality of their products or services [61]. Further, it provides highly smart statistical analysis and online advice to both client and business groups [100]. In the political domain, sentiment analysis is used to analyze people’s orientation and bias toward political campaigning [9, 14]. For e-learning providers, sentiment analysis helps to identify the problems that may occur to learners during the course [42].

In general, sentiment recognition in a text is a process related to the subjective sentences and domain [70, 91]. This dependency has been shown in the topic, time, and writing style. Sentiment analysis is mainly done at the three levels of document [77], sentence [28], and aspect level [34]. In the document-level sentiment analysis, the overall orientation of the document is considered while the internal aspects are disregarded. In the sentence level, only the polarity of the subjective sentences is considered and objective sentences are completely discarded. Finally, in the analysis of sentiments at the aspect level the sentiment corresponding to each aspect is extracted. The final feature in the aspect level consists of a set of pairs including aspect vs sentiment [90, 102].

In general, the three methods of dictionary-based [60, 67], machine learning [74, 99], and the combination of the two previous ones [3, 89] are used for the automatic extraction of sentiments.

Machine learning-based methods using statistical tools, artificial intelligence, and processing tagged databases in the field of natural language extract targeted features, and then classify the newly imported sentences or texts through a training phase based on the tagged views of a specific domain. Conventional approaches to machine learning include Naive Bayes [78, 98], maximum entropy [33, 90], and support vector machine [30 , 93].

Sentiment words play a central role in all sentiment analysis methods. Thus, the construction of a high-quality sentiment dictionary and appropriate scoring has attracted the attention of lots of researchers [29, 86]. Even in machine learning-based methods, a sentiment dictionary can be used to extract sentiment-related features that are more purposeful and efficient in identifying text sentiments [81]. Methods applying manual sentiment dictionaries usually require less training and resources and no annotated corpus [1, 47]. These dictionaries have some other advantages such as the possibility of transforming to different domains and languages [41, 58], better applying linguistic phenomena such as intensifier [75], adding language-dependent features [4] and human beings can understand and modify these dictionaries easier [41, 96].

Thus, sentiment dictionaries including a list of words and phrases with their scores are the most important component of the sentiment analysis methods [1 , 53]. Conventional methods of sentiment recognition using the sentiment compounds and its scores of these dictionaries, efficiently extract statistical features and assign a score to each text [51]. How a dictionary is produced is highly affect the overall accuracy of the polarity detection system [84].

To the best of our knowledge, the attention to the linguistic phenomena has either been too little or not at all in the former dictionaries. In most dictionaries, for example, the effect of the intensifier, such as “very” in combination with sentiment words is not considered or considered to have the effect of adding or subtracting a constant number to sentiment word score or multiplying basic word score to the calculated weight. The major disadvantages of such approaches are the lack of attention to repetition, location of linguistic phenomena, and differences in sentimental words combined with linguistic phenomena. Hence, in polarity calculations, paying attention to linguistic phenomena and their location can greatly improve the efficiency of the method. Among the existing methods, the Senti-N-Gram Dictionary [24] compared to the previous dictionaries considered the heterogeneous effect and the location of multi-linguistic phenomena. However, few covered sentiment expressions and no attention to all possible sentiment combinations are considered as the weaknesses of this dictionary. In addition, because, different negators are considered as invariant phrases in this dictionary, many of Bigram and Trigram combinations, not covered in this dictionary.

Based on previous research’s weakness, the main novelty of this study is to design a public semi-supervised sentiment dictionary using a wide set of sentiment reviews. A hierarchical fuzzy scoring system and addressing the heterogeneous effect of multiple intensifiers in sentiment compound are other novelties of the proposed method. Based on our best knowledge, none of the existing public sentiment dictionaries has these advantages.

In summary, the innovations of this research are first covering all the bigram and trigram combinations including linguistic phenomena combined with a sentiment word by considering the location effect of the intensifier, and second designing a semi-supervised hybrid method based on statistical rules and fuzzy logic for assigning coefficients to each sentiment compound.

The remainder of the present paper is as follows. Section 2 gives an overview of the previous studies and available dictionaries. Section 3 describes the used dictionaries and databases in detail followed by the proposed method. Section 4 compared the proposed dictionary with the existing methods and evaluate the performance of the developed dictionary to the latest and best general dictionaries. Finally, the conclusion is elaborated in Section 5.

2 Related work

In general, a sentiment dictionary is made of a set of single words [48], and each entity within this dictionary is associated with a sentiment score. In some dictionaries [37, 72], this score only indicates the positive, negative, or neutral orientations. Some others [95] contain a limited number of graded sets such as strongly positive, mildly positive, neutral, mildly negative, and strongly negative, while some other dictionaries [8 , 82] use a finite numerical range to express the intensity of sentiment. These methods can be supplemented with other information such as a list of emoticons and semantic rules like how to deal with the negators [65, 84], considering this information when working with short informal texts is important for a higher efficiency [67]. In dictionary-based methods, the in-document sentiment words are searched for classifying based on the existing dictionary [52] and the overall sentiment of the document is determined by the dominant polarity as positive or negative between the indexes [12 , 81]. Generating sentiment dictionaries [46] can be performed via the four methods:

Manual methods including Crowdsourcing [20, 38] and Gamification [36, 88].

Bootstrapping using a set of seed words and syntactic or dependent relationships [32, 68].

Adapting a dictionary from another field using the learning transfer [26 , 97].

Identifying sentiment words by machine learning-based techniques [5 , 97].

This section is divided into the three areas of linguistic phenomena, sentimental dictionaries, and fuzzy logic as the basis of the proposed approach.

2.1 Linguistic phenomena

Although much researches have been focused on the development of supervised and unsupervised systems in sentiment analysis, little attention has been paid to linguistic phenomena in this field [101]. Linguistic phenomena such as the negators and intensifiers are one of the most effective factors in sentiment analysis. Not paying enough attention to the negator or intensifier effect on sentiment words and compounds reduces the efficiency of sentiment analysis systems.

2.1.1 Negators

Negators are considered as one of the most important linguistic phenomena affecting the polarity of sentiment words. Large research [10 , 40] showed that paying attention to linguistic structures such as negators increase the efficiency of sentiment analysis systems.

The effect of negators is considered in four ways

reversing the sentiment word score coming after a negator [25 , 96],

giving a fixed shift of score to sentiment word [54 , 84].

Considering the impact of negation on each individual sentiment compound using statistical or heuristic method [24 , 49]

machine learning-based methods [21, 95].

The present paper applied the inverse hypothesis regarding the complexities of negators and their different effect as changing polarity, emphasizing negativity or making weaker claims [13].

2.1.2 Intensifiers

Paying attention to intensifiers can increase the accuracy and efficiency of sentiment analysis systems [18, 63]. Generally, the intensifiers are divided into amplifiers and downtoners. Intensifiers such as “very” and “entirely” which increase the sentiment of a word are called amplifiers, reinforcers, or overstatements, while intensifiers such as “quite” and “slightly” which decrease the sentiment of a word are known as downtoners or attenuators, [35, 83]. Although none of these words imply polarities on their own, they alter the polarity degree of sentiment words [27]. Calculating the effect of intensifiers is more complicated than simple addition and subtraction [17]. Some methods add or subtract a constant value to exert an intensifying effect on a sentiment word [54, 64]. In [41] the intensifiers were divided into downtoners, weak amplifiers, and strong amplifiers, those of which reducing the sentiment value of the words by 50% are called the downtoners, and those increasing the sentiment value of the words by 50% and 100% are known as weak and strong amplifiers, respectively. In some other methods, each intensifier had a constant coefficient [79 , 96] and its effect is done by multiplying the word score in intensifier coefficient. Also, [24] calculated a different coefficient for each intensifier when placed before each sentiment word. Regarding the increased accuracy of all sentiment analysis techniques when using intensifiers [43], more attention should be paid to generate public sentiment dictionaries supporting intensifiers.

Considering linguistic phenomena, sentiment dictionaries can be classified into the two categories of those regarding linguistic phenomena and those disregarding them. The basic sentiment dictionaries contain only sentiment words and with developing and updating dictionaries, some linguistic rules and phenomena have been added to these dictionaries. Some public dictionaries including linguistic phenomena are reviewed in the next section.

2.2 Sentiment dictionaries regarding one or more linguistic phenomena

SO-CAL dictionary [84] is considered as one of the first sentiment dictionaries including linguistic phenomena. In the new version of this dictionary, the scoring method considers negators, intensifiers and irrealis moods, and lemmatized verbs and nouns, while disregarding the effect of the intensifier location. Instead of changing polarity, shifting has been used in the sentiment words combined with negators such as not, none, nobody, never, etc., reinforcing the negator expressions in the text while reducing the severity of the frequently occurring terms.

The basis of the SentiStrength 1 [87] dictionary consists of 2310 words. This dictionary employs a list of negators, intensifiers, idioms, and emoticons along with the sentiment word list but did not consider pos tagging. All of the words in this dictionary were manually scored and then in the training phase updated.

The SentiFul Dictionary [66] contains several modifiers, intensifiers/inverters, and modal operators. This dictionary was generated automatically using synonymy, antonymy, hyponymy, derivation, and a combination of known words. Further, it was developed using morphology and word manipulations with different prefixes and suffixes.

Lexical TF-IDF Dictionary [23], primarily produced sentiment n-grams with the criteria that one or two intensifiers or negators appear before a sentiment word. The score of sentiment words, intensifiers, and negators are extracted from the VADER 2 [38] and SO-CAL [84] dictionaries, multiplied by their TF-IDF rating to determine a specific weight.

The VADER [38] and Senti-N-Gram [24] dictionaries are two other important public dictionaries that will be explained in detail in the following sections.

2.3 Fuzzy logic

In the classic dictionary generating methods, the scores of the sentimental compounds are calculated using classic mathematical operators. In these methods, some samples of a large database are selected to analyze, and the variance of reviewer value-ratings is ignored. In the proposed method instead of classic operators, fuzzy scores are computed to improve the natural language processing systems in sentiment recognition.

In the proposed method the Gaussian distribution is used, which is the closest fuzzy function to complex natural systems [39]. The main parameters of this fuzzy function include mean and variance, which can be identified and assigned to the sentiment compounds.

3 The proposed method

In this section, two dictionaries and three databases were used in this research are described in detail and the challenges of the former dictionaries are mentioned. In continuation of the discussion, the proposed method in two relatively different parts, has been explained. The flowchart of the generating dictionary part, of the proposed method, is given in Fig. 1.

Fig. 1

Proposed method flowchart.

3.1 The applied dictionaries

The VADER Dictionary: This dictionary [38] contains 7516 sentiment words rated between +4 and –4. The dictionary was generated using the words of the LIWC [71], ANEW [15], and GI [35] dictionaries, as well as a complete list of the Western-style emoticons 3 , acronyms 4 , initialisms, and sentiment idioms. In the first step of the implementation of this dictionary, the extracted words were scored by the Crowdsourcing method via AMT 5 by ten independent individuals on a scale of+4 to –4. In addition to sentiment words, this dictionary includes several intensifiers and provides the five syntax rules of the effect of punctuation, capitalization, intensifiers, the word “but”, and the inverse effect of the negator in trigrams. The weaknesses of this dictionary are, few numbers (only 65) of amplifiers and attenuators and assigning a similar coefficient to all intensifiers. This dictionary discards the heterogeneous effect of the occurrence of multiple intensifiers in sentiment phrase. (for example, see “very good” and “deeply good” scores in Table 1). The VADER sentiment words and its score were used directly in the proposed dictionary.

Table 1
Equal intensifier effect on sentiment words in VADER dictionary

Sentiment phrase Score

good 0.4404

deeply good 0.4927

very good 0.4927

deeply deeply good 0.5379

very deeply good 0.5379

Sentiment phrase	Score
good	0.4404
deeply good	0.4927
very good	0.4927
deeply deeply good	0.5379
very deeply good	0.5379

Senti-N-Gram Dictionary: This dictioanry is the latest public semi manual sentiment dictionary and showed the best results in polarity detection(based on our best knowledge). The basis for this dictionary [24] is the VADER dictionary. This dictionary contains 7516 unigrams, 2415 bigrams, and 305 trigrams. Senti-N-Gram Dictionary is a semi-autonomous dictionary combining sentiment words score in VADER and intensifiers and negators coefficients extracted from a set of reviewer value-ratings belong to Amazon database. In order to generate this dictionary, all the unigrams, bigrams, and trigrams reviewer value-ratings in the Amazon database comments, which are a combination of sentiment words with the intensifiers and negators were extracted. After calculating the percentage of decrease or increase in bigrams scores concerning unigram scores and trigrams compared to bigrams, this percentage multiplied with the VADER score to gain the score of the new bigrams and trigrams. Using this scheme, this dictionary considers the heterogeneous effect of multiple intensifiers in sentiment phrase.

The lack of coverage all sentiment compounds is the major disadvantage of this dictionary. Also, when the sentiment compound in the text has not been scored in the dictionary, only the weight of the sentiment word is considered and the effect of the negator or intensifier is lost.

3.2 Databases

The Amazon website database 6 is used to calculate the score of sentiment compounds in the proposed method. There are about 18 million comments and 80 million contents in 24 different areas in this database. This database is one of the largest and most comprehensive available databases and has been the basis for the proposed semi-automatic dictionary in this research.

Brooke in his master thesis extracted the list of general intensifiers [16] that used as the second database in this research. The coefficients provided by [16] have not been used and the effect of intensifiers in the text is conducted in the proposed method again. The negators are selected based on University of Cambridge standard 7 along with those in the SO-CAL and VADER sentiment dictionaries.

Two manually tagged databases have been used to compare the proposed dictionary with the state-of-the-art dictionaries. First the Taboada database including a collection of eight different domains with 50 positive and negative comments for each domain. This database was collected and tagged by Stanford University in 2004 [85]. The second database 8 is the Pang & Lee database of movie reviews [69], including 1000 positive and 1000 negative reviews on movies.

3.3 Fuzzy pattern extraction of sentiment compounds

In the first step of the dictionary design, all bigram and trigram compounds using the VADER dictionary and the intensifiers in [16] are generated (A1). The sentiment compounds including unigram, bigram and trigram and its reviewer value-rating were extracted from the Amazon database (A2). The intersect of A1 list and A2 combinations were stored as a new list, along with the reviewer value-rating (A3).

Next, a fuzzy pattern of value-ratings was obtained for each unigram, bigram, and trigram compound (A4). A large number of articles in this field have used statistical operators (such as mean) to allocate coefficients or scores effectively to sentiment compounds, while none of them, assign a fuzzy pattern to sentiment compounds.

The initial coefficients, obtaines based on A4 fuzzy model have been used to generate random samples for balancing the number of unigrams, bigram and trigram including a specified sentiment word. For example, when the existing unigrams in the Amazon database are 1000 and a bigram including the same unigram are 50 via the extracted fuzzy pattern for this bigram in the previous step, 950 new scores (value ratings) for this bigram are produced (Eqs. (1) and (2)) (see Table 2 for more explanation on the parameters). (A4)

Table 2
Notations for the algorithms

Symbols Properties

μ_{U
_k}: Unigram statistical mean of sentiment word k’th VADER dictionary

μ_{B
_jk}: Bigram statistical mean includes the sentiment word k and the intensifier j

μ_{T
_ijk}: Trigram statistical mean includes the sentiment word k and the first position intensifier j and the second position intensifier i

${\tilde{μ}}_{B_{jk}}$ : Bigram fuzzy mean includes the sentiment word k and the intensifier j

${\tilde{μ}}_{T_{ijk}}$ : Trigram fuzzy mean includes the sentiment word k and the first position intensifier j and the second position intensifier i

σ_{U
_k}: Unigram fuzzy standard deviation includes the sentiment word k

σ_{B
_jk}: Bigram fuzzy standard deviation includes the sentiment word k and the intensifier j

σ_{T
_ijk}: Trigram fuzzy standard deviation includes the sentiment word k and the first position intensifier j and the second position intensifier i

${\tilde{σ}}_{B_{jk}}$ : Bigram statistical standard deviation includes the sentiment word k and the intensifier j

${\tilde{σ}}_{T_{ijk}}$ : Trigram statistical standard deviation includes the sentiment word k and first position intensifier j and the second position intensifier i

N_{U
_k}: The number of sentiment word k’th VADER dictionary, extracted from Amazon dataset

N_{B
_jk}: Bigram sentiment number includes the intensifier j and the sentiment word k’th VADER dictionary extracted from the Amazon dataset

N_{T
_ijk}: Trigram sentiment number includes first position intensifier j and second position intensifier i and sentiment word k extracted from Amazon dataset

Co_{I
_jk}: Intensifier coefficient j when placed before the sentiment word K in Bigram

Co_{I
_ijk}: Intensifier coefficient i when placed before the intensifier j and sentiment word K in Trigram

So_{VADER
_k} : The score of sentiment word k’th VADER dictionary

So_{B
_jk}: Bigram initial score includes the sentiment word k and the intensifier j

So_{T
_ijk}: Trigram initial score includes the sentiment word k and the first position intensifier j and the second position intensifier i

So_{BN
_jk} : Bigram final score including sentiment word k and intensifier j

So_{TN
_ijk} : Trigram final score including sentiment word k and the first position intensifier j and the second position intensifier i

Co_{IN1_j}: First position intensifier coefficient j

Co_{IN2_i} : Second position intensifier coefficient i

Symbols	Properties
μ_{U _k}:	Unigram statistical mean of sentiment word k’th VADER dictionary
μ_{B _jk}:	Bigram statistical mean includes the sentiment word k and the intensifier j
μ_{T _ijk}:	Trigram statistical mean includes the sentiment word k and the first position intensifier j and the second position intensifier i
${\tilde{μ}}_{B_{jk}}$ :	Bigram fuzzy mean includes the sentiment word k and the intensifier j
${\tilde{μ}}_{T_{ijk}}$ :	Trigram fuzzy mean includes the sentiment word k and the first position intensifier j and the second position intensifier i
σ_{U _k}:	Unigram fuzzy standard deviation includes the sentiment word k
σ_{B _jk}:	Bigram fuzzy standard deviation includes the sentiment word k and the intensifier j
σ_{T _ijk}:	Trigram fuzzy standard deviation includes the sentiment word k and the first position intensifier j and the second position intensifier i
${\tilde{σ}}_{B_{jk}}$ :	Bigram statistical standard deviation includes the sentiment word k and the intensifier j
${\tilde{σ}}_{T_{ijk}}$ :	Trigram statistical standard deviation includes the sentiment word k and first position intensifier j and the second position intensifier i
N_{U _k}:	The number of sentiment word k’th VADER dictionary, extracted from Amazon dataset
N_{B _jk}:	Bigram sentiment number includes the intensifier j and the sentiment word k’th VADER dictionary extracted from the Amazon dataset
N_{T _ijk}:	Trigram sentiment number includes first position intensifier j and second position intensifier i and sentiment word k extracted from Amazon dataset
Co_{I _jk}:	Intensifier coefficient j when placed before the sentiment word K in Bigram
Co_{I _ijk}:	Intensifier coefficient i when placed before the intensifier j and sentiment word K in Trigram
So_{VADER _k} :	The score of sentiment word k’th VADER dictionary
So_{B _jk}:	Bigram initial score includes the sentiment word k and the intensifier j
So_{T _ijk}:	Trigram initial score includes the sentiment word k and the first position intensifier j and the second position intensifier i
So_{BN _jk} :	Bigram final score including sentiment word k and intensifier j
So_{TN _ijk} :	Trigram final score including sentiment word k and the first position intensifier j and the second position intensifier i
Co_{IN1_j}:	First position intensifier coefficient j
Co_{IN2_i} :	Second position intensifier coefficient i

$\begin{matrix} μ_{B_{jk}}, σ_{B_{jk}}, N_{B_{jk}} \\ \Rightarrow PDF (μ_{B_{jk}}, σ_{B_{jk}}, N_{B_{jk}}) \\ \Rightarrow ({\tilde{μ}}_{B_{jk}}, {\tilde{σ}}_{B_{jk}}, N_{U_{k}}) \end{matrix}$ (1) $\begin{matrix} μ_{T_{ijk}}, σ_{T_{ijk}}, N_{T_{ijk}} \\ \Rightarrow PDF (μ_{T_{ijk}}, σ_{T_{ijk}}, N_{T_{ijk}}) \\ \Rightarrow ({\tilde{μ}}_{T_{ijk}}, {\tilde{σ}}_{T_{ijk}}, N_{U_{k}}) \end{matrix}$ (2)

3.4 Calculating the intensifier coefficient

After equating the number of samples by the reviewer value-rating fuzzy pattern described in the previous section, the bigram score is calculated via simple averaging for the new samples, then the computed bigram score is divided by the unigram population mean to calculate the initial intensifier coefficient of the first position intensifier (Equation (3)) (A5). It is similarly done using the mean of trigrams and bigrams to calculate the second position intensifier coefficient (Equation (4)) (A6). $\begin{matrix} (μ_{U_{k}}, & σ_{U_{k}}, & N_{U_{k}}) \\ ({\tilde{μ}}_{B_{jk}}, & {\tilde{σ}}_{B_{jk}}, & N_{U_{k}}) \\ ({\tilde{μ}}_{T_{ijk}}, & {\tilde{σ}}_{T_{ijk}}, & N_{U_{k}}) \end{matrix} \Rightarrow {\begin{matrix} {CO}_{I_{jk}} = \frac{{\tilde{μ}}_{B_{jk}}}{μ_{U_{k}}} (3) \\ {CO}_{I_{ijk}} = \frac{{\tilde{μ}}_{T_{ijk}}}{{\tilde{μ}}_{B_{jk}}} (4) \end{matrix}$

Then, in order to get the result closer to human data, the coefficient of the intensifier calculated for kth sentiment word in Equation (3) is multiplied by the score of same word from the VADER dictionary (A7). In other words, the bigrams score is updated using the scores in the VADER dictionary and calculated coefficients in the previous step (Equation (5)). ${So}_{B_{jk}} = {Co}_{I_{jk}} * {So}_{{VADER}_{k}}$ (5)

The primary score of trigrams is recalculated using the obtained score in Equation (5) and the obtained coefficient in Equation (4) (Equation (6)) (A8). ${So}_{T_{ijk}} = {Co}_{I_{ijk}} * {So}_{B_{jk}}$ (6)

Increment–decrement percentage value for n-grams, Score warping, verification and refinement of the score of n-gram was done similar to [24] to enhance accuracy.

The corrected scores were used to recalculate intensifier coefficients. These coefficients are averaged for different sentiment words per intensifier to get the final intensifier coefficient of the first position based on Equation (7) (A9). $\forall j \to {Co}_{IN 1_{j}} = avg ({Co}_{I_{jk}})$ (7)

After determining the final coefficient of the first position intensifier, the bigrams score is updated again (A10, Equation (8)), the new scores are used to derive the second intensifier coefficients belong to trigram via Eqs. (9) and (10) (A11-A12). ${So}_{{BN}_{jk}} = {Co}_{IN 1_{j}} * P_{{VADER}_{k}}$ (8) ${Co}_{I_{ijk}} = \frac{{So}_{T_{ijk}}}{{So}_{{BN}_{jk}}}$ (9) $\forall i \to {Co}_{IN 2_{i}} = avg ({Co}_{I_{ijk}})$ (10)

In the proposed method, the final coefficients of the intensifier in the first and second positions are a combination of fuzzy logic, statistical methods, reviewer value-rating of Amazon database and VADER manual dictionary. The combination of the above steps minimizes errors in calculating the intensifier coefficient.

Based on Fig. 1, the generated dictionary consists of 7516 sentiment words (based on VADER Dictionary), 215 intensifiers and 53 negators. The score of sentiment words is chosen based on VADER. The two coefficients assigned to each intensifier based on its position. The 53 negators has an inverse coefficient –1. As a glance, the score of each sentiment can be calculated, based on Table 1 formula, using the following equations, as: ${So}_{U_{k} =} {So}_{{VADER}_{k}}$ (11) ${So}_{{BN}_{jk}} = {Co}_{IN 1_{j}} * {So}_{{VADER}_{k}}$ (12) ${So}_{{TN}_{ijk}} = {Co}_{IN 2_{i}} * {Co}_{IN 1_{j}} * {So}_{{VADER}_{k}}$ (13)

Base on Eqs. (12-13) and the scores of “enjoy” and “bad” in VADER dictionary that are 2.3, –2.5 respectively and using Table 3 values we can calculate the score of “very big bad” and “very deeply enjoyed” as:

Table 3

The calculated coefficients for some intensifiers considering their position on sentimental phrase

intensifier	Second position	First position
deeply	1.805689	2.490525
very	1.452547	2.152212
big	1.200473	2.086358

very big bad = 1.45*2.08*(–2.5)=–7.54

very deeply enjoyed = 1.45*2.5*2.3 = 8.34

In the result section, two polarity document classification algorithms are implemented. In the first polarity detection algorithm [45], score of sentiment phrases in each sentence based on each dictionary are extracted and their mean is calculated. Then, the average of the various sentences is added together and a general assessment of the polarity of the document is made. In the second algorithm proposed in [24], similar to the first algorithm, score of sentiment phrases based on each dictionary are extracted, added together and the polarity of each sentence is calculated. Finally, the number of positive and negative sentences are counted and the higher number determines the document polarity. The document polarity is considered to be negative when the number is equal.

4 Results

The result section is divided into two parts. In the first part, the results of the fuzzy probability density function and fuzzy statistical tests in calculating the initial scores are presented for several n-gram samples. In the second part, based on different validity criteria such as Recall, Precision, and F-measure, the Accuracy of the proposed system against the state-of-the-art methods in two standard databases in different domains is investigated.

4.1 Fuzzy pattern

In the first step, the fuzzy bigram and trigram model should be obtained based on the statistical model and the number of samples in unigram, bigram, and trigram, and then the bigram and trigram parameters are calculated again by generating sufficient samples and homogenizing (Equations (1) and (2)). The calculated fuzzy pattern for “good”, “very good”, and “very very good” is shown in Fig. 2.

Fig. 2

The Fuzzy diagram for the three terms “Good”, “Very Good” and “Very Very good”.

The pattern output is restricted to the interval of 1 to 5 considering the actual scoring of sentences in the Amazon database. The standard deviation of bigram decreased in comparison with unigram due to the proximity of scores for the sentences in bigram. In addition, due to the proximity of scores for the sentences in trigram, its standard deviation decreased compared with bigram (Fig. 2).

Table 4 shows the initial statistical mean and the corresponding fuzzy mean of the distribution after homogenizing a sample to indicate the effect of homogenizing in the obtained averages. Based on Table 4, the mean varied about 2 to 5% in trigram and bigram versus simple mean.

Table 4

Statistical and fuzzy results of a sample of Unigram, Bigram, Trigram

	Mean		std
	Statistical	Fuzzy
Good	4.3306	—–	0.925
Very good	4.5013	4.3992	0.785
Very very good	4.5634	4.4776	0.670

This step is equivalent to Equations (1) and (2). The columns 2 and 3 of Table 4 are the mean and standard deviation of the samples, namely ${\tilde{μ}}_{T_{jk}}, {\tilde{μ}}_{B_{jk}}, {\tilde{σ}}_{B_{jk}}, {\tilde{σ}}_{T_{jk}}$ in Equations (1) and (2).

4.2 The proposed method evaluation

The proposed dictionary is compared with two state of the art dictionaries in this field, namely VADER [38] and Senti-N-Gram [24]. A comparison was made between the two databases of Taboada [85] and Pang & Lee [69] described in Section 3 to demonstrate the efficiency of the proposed dictionary. The common criteria of True Positives (TP) (the positive documents separated truly), True Negatives (TN) (the negative documents separated truly), False Positives (FP) (the documents with a negative polarity which was mistakenly identified as positive), and False Negatives (FN) (the documents with a positive polarity which was mistakenly identified as negative) were applied for the comparison. Using these criteria, the four parameters of Precision, Recall, F-measure, and Accuracy were obtained. The relationships for these four criteria are given in Equations (14–17).

Precision: The precision of a method is the ratio of correctly classified positive documents to the total classified positive documents. $Precision (P) = \frac{TP}{TP + FP}$ (14)

Recall: Recall is the ratio of correctly classified positive documents to all positive documents. This criterion usually shows higher value than precision because it evaluates the method in positive documents in which most methods perform more efficiently. $Recall (R) = \frac{TP}{TP + FN}$ (15)

F-measure: It is the harmonic mean of precision and recall. $F - measure (F) = \frac{2 * P * R}{P + R}$ (16)

Accuracy: It indicates the performance of the system in all documents. $Accuracy (A) = \frac{TP + TN}{TP + TN + FP + FN}$ (17)

For the evaluation to be done in similar conditions, the Senti-N-Gram dictionary and proposed method were made using similar samples of amazon database so the conditions for comparison were completely the same.

Table 5 presents the accuracy of the three dictionaries in both databases and indicates that the proposed method has at least 2.45% better accuracy in both databases than all previous methods.

Table 5

Comparison of Accuracy Parameter Based on the Classification of Documents at Sentence Level Using VADER, Senti-N-Gram Dictionaries, and Proposed method

Datasets	First classification method [45]			Second classification method [24]
	VADER	Senti-N-Gram	Proposed	VADER	Senti-N-Gram	Proposed
Epinions	62	61.75	67.75	63.5	63.75	69
Movie review	63.5	63.75	67.05	63.95	63.8	66.35

Table 6 shows accuracy increase using first polarity document classification algorithm [45], in all overall results belong to domain-specific comparison. This table shows the proposed method in all cases is more efficient than the previous methods, especially in the negative documents.

Table 6

Comparison of Accuracy Parameter Based on Classification Method [45] Using VADER, Senti-N-Gram and Suggested dictionary in Different Areas

Datasets	VADER			Proposed			Senti-N-Gram
	Positive	Negative	Positive	Negative	overall	overall	Positive	Negative	overall
BOOKS	100	36	68	92	32	62	88	56	72
CARS	100	28	64	100	32	66	100	32	66
COMPUTERS	100	32	66	100	36	68	100	44	72
COOKWARE	100	16	58	100	12	56	100	16	58
HOTELS	100	8	54	100	20	60	100	36	68
MOVIES	96	32	64	92	28	60	96	32	64
MUSIC	92	24	58	92	20	56	96	32	64
PHONES	92	36	64	92	40	66	100	56	78

As shown in Table 6, the greatest improvement in detecting negative expressions is observed in the domains HOTELS, BOOKS and PHONES with values of 80, 55 and 40%, respectively. The highest increase is related to the PHONES domain, with 12% overall improvement.

Table 7 compares the precision, recall, and F-measure in three dictionaries. Only in BOOKS domain, the recall of the proposed method is less than other methods but the higher precision value in the proposed method based on better detection of negative documents, overcomes this weakness. The value 1 in the recall (R) columns of three dictionaries in Table 7 shows all dictionaries have good results in positive document detection and the main challenge is in negative document classification. The main advantage of the proposed dictionary, is its correctness in negative document classification in all domains (see Table 6 column negative).

Table 7

Comparison of Precision, Recall, and F-measure Parameters Based on Classification Method [45] Using VADER, Senti-N-Gram and Proposed Dictionaries in Different Areas

	VADER			Senti-N-Gram			Proposed
	P	R	F	P	R	F	P	R	F
BOOKS	0.61	1	0.76	0.58	0.92	0.71	0.67	0.88	0.76
CARS	0.58	1	0.74	0.6	1	0.75	0.6	1	0.75
COMPUTERS	0.6	1	0.75	0.61	1	0.76	0.64	1	0.78
COOKWARE	0.54	1	0.7	0.53	1	0.69	0.54	1	0.7
HOTELS	0.52	1	0.69	0.56	1	0.71	0.61	1	0.76
MOVIES	0.59	0.96	0.73	0.56	0.92	0.7	0.59	0.96	0.73
MUSIC	0.55	0.92	0.69	0.54	0.92	0.68	0.59	0.96	0.73
PHONES	0.59	0.92	0.72	0.61	0.92	0.73	0.69	1	0.82

For showing proposed dictionary accuracy in different conditions, the simulations repeated using second polarity detection algorithm explained in the last paragraph of section 3 [45]. In this analysis, document polarity detection method is done based on counting the number of positive and negative sentences in the document and choosing higher number as selected polarity [45]. The better results of proposed method can be observed versus two Senti-N-Gram and VADER dictionaries (Tables 8 and 9).

Table 8

Comparison of Accuracy Parameter Based on Classification Method [24] Using VADER, Senti-N-Gram and Suggested Dictionaries in Different Areas

Datasets	VADER			Senti-N-Gram			Proposed
	Positive	Negative	overall	Positive	Negative	overall	Positive	Negative	overall
BOOKS	100	36	68	96	40	68	96	48	72
CARS	100	28	64	100	32	68	100	36	68
COMPUTERS	96	40	68	96	36	66	92	40	66
COOKWARE	100	12	56	100	20	60	100	20	60
HOTELS	100	20	60	100	16	58	100	28	64
MOVIES	92	36	64	96	24	60	100	40	70
MUSIC	96	20	58	92	20	56	100	36	68
PHONES	96	44	70	92	60	76	92	76	84

Table 9

Comparison of Precision, Recall and F-measure Parameters Based on Classification Method [24] Using VADER, Senti-N-Gram Dictionaries and Proposed Dictionaries in Different Areas

	VADER			Senti-N-Gram			Proposed
	P	R	F	P	R	F	P	R	F
BOOKS	0.61	1.00	0.76	0.62	0.96	0.75	0.65	0.96	0.77
CARS	0.58	1.00	0.74	0.60	1.00	0.75	0.61	1.00	0.76
COMPUTERS	0.62	0.96	0.75	0.60	0.96	0.74	0.61	0.92	0.73
COOKWARE	0.53	1.00	0.69	0.56	1.00	0.71	0.56	1.00	0.71
HOTELS	0.56	1.00	0.71	0.54	1.00	0.70	0.58	1.00	0.74
MOVIES	0.59	0.92	0.72	0.56	0.96	0.71	0.63	1.00	0.77
MUSIC	0.55	0.96	0.70	0.54	0.92	0.68	0.61	1.00	0.76
PHONES	0.63	0.96	0.76	0.70	0.92	0.79	0.79	0.92	0.85

As shown in Table 8, the proposed dictionary increases the number of negative document detections in all eight domains. It reduces the error in positive documents in the MOVIES and MUSIC domains to zero. The highest improvement is in PHONES domain, similar to previous method, although some results are different. For example, in VADER dictionary, PHONES domain, the second classification method using proposed dictionary shows 32 increase in classification of negative documents while the first classification method only shows 20 increase. In this table, the proposed method increased HOTELS, MUSICS and BOOKS accuracy in negative documents 80, 40 and 20%, respectively.

According to the Table 9 results, the F-measure and precision results of proposed method are considered as a valuable performance increasement in all domains except COMPUTERS (for example F-measure improved 8% vs Senti-N-Gram in MUSIC domain). In overall result, on average the suggested method shows 4% and 4.6% better results than Senti-n-gram and VADER dictionary in precision criteria respectively, and 3.2% better results than both dictionaries in F-measure. In positive document classification (recall criteria) the suggested dictionary results average is similar to two previous dictionaries.

5 Conclusion

Due to the wide range of sentiment analysis applications and increasing the need for automated algorithms for document and sentiment analysis, a hybrid scheme for training semi-manual sentiment dictionary was proposed in the present paper.

The proposed method, assigned a fuzzy coefficient to each intensifier in bigrams and trigrams regarding the position of the intensifier towards the sentiment word that enhanced the efficiency of the existing dictionaries in document polarity recognition.

In the proposed scheme, the intensifier coefficients were corrected during several stages using the fuzzy pattern of review value ratings. Also, the intensifier place relative to the sentiment word and the mutual-effect between the polarity of the sentiment word vs the intensifier was considered. Therefore, two different coefficients were obtained for each intensifier according to the first or second position regarding to sentiment word. This scheme leads to a more efficient score assignment based on its fuzzy and both machine-learning and reviewer value-ratings error correction steps, a wider range of combinations, and enhance accuracy, especially in the negative documents than conventional state of the art public sentiment dictionaries. Finally, the proposed method was implemented on several standard databases and its results were compared with two state of the art dictionaries. Comparing results indicated the accuracy of the proposed method was increased about 7% compared to the latest methods in this field. As future work, the irrealis role in polarity detection can be considered and added to proposed dictionar.

Footnotes

Valence aware dictionary for sentiment reasoning.

Amazon Mechanical Turk.

References

Abdi

, Shamsuddin

S.M.

, Hasan

and Piran

, Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion, Information Processing and Management 56 (2019), 1245–1259.

Ainin

, Feizollah

, Anuar

N.B.

and Abdullah

N.A.

, Sentiment analyses of multilingual tweets on halal tourism, Tourism Management Perspectives 34 (2020), 100658.

Alharbi

J.R.

and Alhalabi

W.S.

, Hybrid approach for sentiment analysis of twitter posts using a dictionary-based approach and fuzzy logic methods: Study case on cloud service providers, International Journal on Semantic Web and Information Systems 16 (2020), 116–145.

Araque

, Corcuera-Platas

, Sánchez-Rada

J.F.

and Iglesias

C.A.

, Enhancing deep learning sentiment analysis with ensemble techniques in social applications, Expert Systems with Applications 77 (2017), 236–246.

Araque

, Zhu

and Iglesias

C.A.

, A semantic similarity-based perspective of affect lexicons for sentiment analysis, Knowledge-Based Systems 165 (2019), 346–359.

Asghar

M.Z.

, Ullah

, Ahmad

and Khan

, Opinion spam detection framework using hybrid classification scheme, Soft Computing, (2019).

Avanc

L. V

and Nunes

M.G. V

, Lexicon-based Sentiment Analysis for Reviews of Products in Brazilian Portuguese, (2014), 10–14.

Baccianella

, Esuli

and Sebastiani

, SENTIWORDNET 3.0: An enhanced lexical resource for sentiment analysis and opinion mining, Proceedings of the 7th International Conference on Language Resources and Evaluation, LREC 2010. (2010), 2200–2204.

Badaro

, Baly

, Hajj

, El-Hajj

, Shaban

K.B.

, Habash

, Al-Sallab

and Hamdi

, A survey of opinion mining in Arabic: A comprehensive system perspective covering challenges and advances in tools, resources, models, applications, and visualizations, ACM Transactions on Asian and Low-Resource Language Information Processing 18 (2019).

10.

Barnes

, Velldal

and Øvrelid

, Improving sentiment analysis with multi-task learning of negation, 1 (2020), 1–23.

11.

Benamara

, Chardon

, Mathieu

, Popescu

and Asher

, How do Negation and Modality Impact on Opinions? Proceedings of theWorkshop on Extra-Propositional Aspects of Meaning in Computational Linguistics Association for Computational Linguistics, (2012), 10–18.

12.

Bhadane

, Dalal

and Doshi

, Sentiment analysis: Measuring opinions, Procedia Computer Science 45 (2015), 808–814.

13.

Blanco

and Moldovan

, Some Issues on Detecting Negation from Text, Proceedings of the 24th Florida Artificial Intelligence Research Society Conference (FLAIRS-24). (2011), 228–233.

14.

Bose

, Dey

R.K.

, Roy

and Sarddar

, Analyzing Political Sentiment Using Twitter Data, in: Information and Communication Technology for Intelligent Systems, Springer, Singapore, Springer, Singapore, 2019, pp. 427–436.

15.

Bradley

and Lang

, Affective norms for English words (ANEW): Instruction manual and affective ratings, in: Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings, 1999, pp. 25–36.

16.

Brooke

, A Semantic Approach To Automated Text Sentiment Analysis, 2009.

17.

Brooke

, Tofiloski

and Taboada

, Cross-linguistic sentiment analysis: From English to Spanish, in: International Conference Recent Advances in Natural Language Processing, RANLP, 2009, pp. 50–54.

18.

Carrillo-de-albornoz

and Plaza

, An emotion-based model of negation, intensifiers, and modality for polarity and intensity classification, Journal of the American Society for Information Science and Technology 64 (2013), 1618–1633.

19.

Chakraborty

, Bhattacharyya

, Bag

and Hassanien

A.A.

, Sentiment Analysis on a Set of Movie Reviews Using Deep Learning Techniques, Elsevier Inc., 2019.

20.

Chung

C.K.

and Pennebaker

J.W.

, Linguistic Inquiry and Word Count (LIWC), Applied Natural Language Processing, (2013), 206–229.

21.

Cruz

N.P.

, Taboada

and Mitkov

, A Machine-Learning Approach to Negation and Speculation Detection for Sentiment Analysis, Journal of the Association for Information Science and Technology 67 (2015), 2118–2136.

22.

Dessí

, Dragoni

, Fenu

, Marras

and Recupero

D.R.

, Deep Learning Adaptation with Word Embeddings for Sentiment Analysis on Online Course Reviews, in: Springer, Singapore, 2020, pp. 57–83.

23.

Dey

, Jenamani

and Thakkar

J.J.

, Lexical TF-IDF: An n-gram Feature Space for Cross-Domain Classification of Sentiment Reviews, in: International Conference on Pattern Recognition and Machine Intelligence, 2017, pp. 380–386.

24.

Dey

, Jenamani

and Thakkar

J.J.

, Senti-N-Gram: An n-gram lexicon for sentiment analysis, Expert Systems with Applications 103 (2018), 92–105.

25.

Diamantini

, Mircoli

, Potena

and Storti

, Social information discovery enhanced by sentiment analysis techniques, Future Generation Computer Systems 95 (2019), 816–828.

26.

Dong

and De Melo

, A helping hand: Transfer learning for deep sentiment analysis, ACL 2018–56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) 1 (2018), 2524–2534.

27.

Dragut

E.C.

and Fellbaum

, The Role of Adverbs in Sentiment Analysis, in: A Workshop in Honor of Chuck Fillmore (1929–2014), 2014, pp. 38–41.

28.

Eng

, Nawab

M.R.I.

and Shahiduzzaman

K.M.

, Improving Accuracy of The Sentence-Level Lexicon-Based Sentiment Analysis Using Machine Learning, International Journal of Scientific Research in Computer Science Engineering and Information Technology 3307 (2021), 57–68.

29.

Fernández-Gavilanes

, García-Méndez

, Costa-Montenegro

and González-Castaño

F.J.

, Creating emoji lexica from unsupervised sentiment analysis of their descriptions, Expert Systems with Applications 103 (2018), 74–91.

30.

Fikri

and Sarno

, A comparative study of sentiment analysis using SVM and Senti Word Net, Indonesian Journal of Electrical Engineering and Computer Science 13 (2019), 902–909.

31.

, Abbasi

, Zeng

and Chen

, Sentimental Spidering: Leveraging Opinion Information in Focused Crawlers, ACM Transactions on Information Systems 30 (2012), 1–30.

32.

Giachanou

, Gonzalo

and Crestani

, Propagating sentiment signals for estimating reputation polarity, Information Processing & Management 56 (2019), 102079.

33.

Giang

N.T.P.

, Dien

T.T.

and Khoa

T.T.M.

, Sentiment Analysis for University Students’ Feedback, Advances in Intelligent Systems and Computing 1130 AISC (2020), 55–66.

34.

Gupta

, Singh

V.K.

, Mukhija

and Ghose

, Aspect-based sentiment analysis of mobile reviews, Journal of Intelligent and Fuzzy Systems 36 (2019), 4721–4730.

35.

Hartman

J.J.

, Stone

P.J.

, Dunphy

D.C.

, Smith

M.S.

and Ogilvia

D.M.

, The General Inquirer: A Computer Approach to Content Analysis, American Sociological Review 32 (1967), 859.

36.

Hong

, Kwak

, Baek

and Moon

, Tower of babel: A crowdsourcing game building sentiment lexicons for resource-scarce languages, Proceedings of the 22nd International Conference on World Wide Web, (2013), 549–556.

37.

and Liu

, Mining and summarizing customer reviews, Proceedings of the 2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – KDD ’04. (2004), 168.

38.

Hutto

C.J.J.

, Gilbert

E.E.

, VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text, in: Eighth International AAAI Conference on Weblogs and Social Media, 2014, pp. 216–225.

39.

Jain

and Lobiyal

D.K.

, Fuzzy Hindi wordnet and word sense disambiguation using fuzzy graph connectivity measures, ACM Transactions on Asian and Low-Resource Language Information Processing 15 (2015).

40.

Jia

, Yu

and Meng

, The effect of negation on sentiment analysis and retrieval effectiveness, in: Proceedings of the 18th ACM Conference on Information and Knowledge Management, 2009, pp. 1827–1830.

41.

Jurek

, Mulvenna

M.D.

and Bi

, Improved lexicon-based sentiment analysis for social media analytics, Security Informatics 4 (2015), 9.

42.

Kechaou

and Ben

, Improving e-learning with sentiment analysis of users’ opinions, in: 2011 IEEE Global Engineering Education Conference (EDUCON), IEEE, 2011, pp. 1032–1038.

43.

Kennedy

and Inkpen

, Sentiment classification of movie reviews using contextual valence shifters, Computational Intelligence 22 (2006), 110–125.

44.

Keshavarz

and Abadeh

M.S.

, Accurate frequency-based lexicon generation for opinion mining, Journal of Intelligent and Fuzzy Systems 33 (2017), 2223–2234.

45.

Khan

, Baharudin

and Khan

, Sentiment Classification Using Sentence-level lexical Based semantic orientation of Online reviews, Trends in Applied Sciences Research 6 (2011), 1141–1157.

46.

Khoo

C.S.G.

and Johnkhan

S.B.

, Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons, Journal of Information Science 44 (2018), 491–511.

47.

Kirchner

A.N.

, An exploration of a financial lexicon-based approach to sentiment analysis and its application to financial news and reports, Orthern Illinois University. (2019), 1–22.

48.

Kiritchenko

, Mohammad

S.M.

and Canada

, The Effect of Negators,Modals, and Degree Adverbs on Sentiment Composition, in: In Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA), 2017, pp. 43–52.

49.

Kiritchenko

, Zhu

and Mohammad

S.M.

, Sentiment analysis of short informal texts, Journal of Artificial Intelligence Research 50 (2014), 723–762.

50.

, Mao

, Xu

, Li

and Zhang

, Bag-of-Concepts representation for document classification based on automatic knowledge acquisition from probabilistic knowledge base, Knowledge-Based Systems 193 (2020), 105436.

51.

Liu

, Sentiment analysis and subjectivity, Handbook of Natural Language Processing, (2010), 627–666.

52.

Liu

, Sentiment Analysis and Opinion Mining, Morgan & Claypool Publishers, 2012.

53.

Liu

and Zhang

, A survey of opinion mining and sentiment analysis, in: Mining Text Data, Springer US, Boston, MA, 2012, pp. 415–463.

54.

Liu

, Seneff

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing 1 (2009), 161–169 Review sentiment scoring via a parse-and-paraphrase paradigm, Volume.

55.

Liu

, Bi

J.W.

and Fan

Z.P.

, A method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm,395}, Information Sciences 394{– (2017), 38–52.

56.

, Zhu

, Xu

, Zhang

, Wu

and Guo

, Bi-gru sentiment classification for chinese based on grammar rules and bert, International Journal of Computational Intelligence Systems 13 (2020), 538–548.

57.

Mäntylä

M. V.

, Graziotin

and Kuutila

, The evolution of sentiment analysis—A review of research topics, venues, and top cited papers, Computer Science Review 27 (2018), 16–32.

58.

Mihalcea

, Banea

and Wiebe

, Learning multilingual subjective language via cross-lingual projections, in: ACL 2007 – Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, 2007, pp. 976–983.

59.

Mirtalaie

M.A.

, Hussain

O.K.

, Chang

and Hussain

F.K.

, Extracting sentiment knowledge from pros/cons product reviews: Discovering features along with the polarity strength of their associated opinions, Expert Systems with Applications 114 (2018), 267–288.

60.

Mohammad

S.M.

, Kiritchenko

and Zhu

, NRC-Canada: Building the state-of-the-art in sentiment analysis of tweets, in: *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, 2013, pp. 321–327.

61.

, Zheng

, Zhang

and Zhang

, Research on Customer Satisfaction Based on Multidimensional Analysis, International Journal of Computational Intelligence Systems 14 (2021), 605–616.

62.

Mudgal

and Khunteta

, Handling Double Intensifiers in Feature-Level Sentiment Analysis Based on Movie Reviews, in: 5th International Conference on Artificial Intelligence and Applications, 2020, pp. 383–392.

63.

Mukhtar

, Khan

M.A.

and Chiragh

, Lexicon-based approach outperforms Supervised Machine Learning approach for Urdu Sentiment Analysis in multiple domains, Telematics and Informatics 35 (2018), 2173–2183.

64.

Mukhtar

, Khan

M.A.

, Chiragh

and Nazir

, Identification and handling of intensifiers for enhancing accuracy of Urdu sentiment analysis, Expert Systems 35 (2018), 1–12.

65.

Neviarouskaya

, Prendinger

and Ishizuka

, Textual Affect Sensing for Sociable and Expressive, International Conference on Affective Computing and Intelligent Interaction, Springer, Berlin, Heidelberg, (2007), 218–219.

66.

Neviarouskaya

, Prendinger

and Ishizuka

, SentiFul: A lexicon for sentiment analysis, IEEE Transactions on Affective Computing 2 (2011), 22–36.

67.

Nielsen

, A new ANEW: Evaluation of a word list for sentiment analysis in microblogs, CEUR Workshop Proceedings 718 (2011), 93–98.

68.

Oliveira

, Cortez

and Areal

, Stock market sentiment lexicon acquisition using microblogging data and statistical measures, Decision Support Systems 85 (2016), 62–73.

69.

Pang

and Lee

, A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts, in: In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, 2004.

70.

Pang

and Lee

, Opinion mining and sentiment analysis, 2008.

71.

Pennebaker

, Boyd

, Jordan

and Blackburn

, The development and psychometric properties of LIWC2015, LIWC2015, (2015).

72.

Pennebaker

J.W.

, Pennebaker

J.W.

, Francis

M.E.

, Booth

R.J.

, Francis

M.E.

, Pennebaker

J.W.

, Francis

M.E.

and Booth

R.J.

, LIWC2007: Linguistic inquiry and word count, Austin, Texas: Liwc. Net, (2007), 1–22.

73.

Piryani

, Gupta

and Singh

V.K.

, Movie Prism: A novel system for aspect level sentiment profiling of movies, Journal of Intelligent and Fuzzy Systems 32 (2017), 3297–3311.

74.

Piryani

, Piryani

, Singh

V.K.

and Pinto

, Sentiment analysis in Nepali: Exploring machine learning and lexicon-based approaches, Journal of Intelligent and Fuzzy Systems 39 (2020), 2201–2212.

75.

Polanyi

and Zaenen

, Contextual valence shifters, in: AAAI Spring Symposium – Technical Report, Springer-Verlag, Berlin/Heidelberg, 2005, pp. 106–111.

76.

Rani

and Kumar

, A Sentiment Analysis System to Improve Teaching and Learning, Computer 50 (2017), 36–43.

77.

Ren

and Wang

, Sentiment analysis of text based on three-way decisions, Journal of Intelligent and Fuzzy Systems 33 (2017), 245–254.

78.

Sailunaz

and Alhajj

, Emotion and sentiment analysis from Twitter text, Journal of Computational Science 36 (2019), 101003.

79.

Satthar

F.S.

, Modelling SO-CAL in an inheritance-based sentiment analysis framework, 2015 Imperial College Computing Student Workshop (ICCSW 2015), (2015), 46–53.

80.

Spatiotis

, Periko

, Mporas

and Paraskevas

, Sentiment Analysis of Teachers Using Social Information in Educational Platform Environments, International Journal on Artificial Intelligence Tools 29 (2020).

81.

Sun

, Luo

and Chen

, A review of natural language processing techniques for opinion mining systems, Information Fusion 36 (2017), 10–25.

82.

Sweeney

and Whissell

, A Dictionary Of Affect IN Language: I. Establishment AND Preliminary Validation, Perceptual and Motor Skills 59 (1984), 695–698.

83.

Taboada

, Sentiment Analysis: An Overview from Linguistics, Annual Review of Linguistics 2 (2016), 325–347.

84.

Taboada

, Brooke

, Tofiloski

, Voll

and Stede

, Lexicon-based methods for sentiment analysis, Computational Linguistics 37 (2011), 267–307.

85.

Taboada

and Grieve

, Analyzing Appraisal Automatically, AAAI Spring Symposium – Technical Report 2004 (2004), 158–161.

86.

Tang

, Wei

, Qin

, Zhou

and Liu

, T.L.-P. of coling 2014, undefined the, undefined 2014, Building large-scale twitter-specific sentiment lexicon: A representation learning approach, COLING 2014 – 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers, (2014), 172–182.

87.

Thelwall

, Buckley

, Paltoglou

, Cai

and Kappas

, Sentiment strength detection in short informal text, Journal of the American Society for Information Science and Technology 61 (2010), 2544–2558.

88.

Thisone

C.M.

, Sentiment Analysis Using a Novel Human Computation Game, Proceedings of the 3rd Workshop on the People’s Web Meets NLP: Collaboratively Constructed Semantic Resources and Their Applications to NLP, (2012), 1–9.

89.

Tran

T.K.

and Phan

T.T.

, A hybrid approach for building a Vietnamese sentiment dictionary, Journal of Intelligent and Fuzzy Systems 35 (2018), 967–978.

90.

Tripathy

, Agrawal

and Rath

S.K.

, Classification of sentiment reviews using n-gram machine learning approach, Expert Systems with Applications 57 (2016), 117–126.

91.

Turney

P.D.

, P. D., Thumbs up or thumbs down? sentiment classification using machine learning techniques, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics – ACL ’02, (2001), 417.

92.

Vasudha Rani

and Sandhya Rani

, Identification of ontologies of prediabetes using SVM sentiment analysis, Advances in Intelligent Systems and Computing 1054 (2020), 535–550.

93.

, Sharma

, Kumar

, Son

L.H.

, Pham

B.T.

, Bui

D.T.

, Priyadarshini

, Sarkar

and Le

, Crime rate detection using social media of different crime locations and Twitter part-of-speech tagger with Brown clustering, Journal of Intelligent and Fuzzy Systems 38 (2020), 4287–4299.

94.

Wang

, Subhan

, Shamshirband

, Asghar

M.Z.

, Ullah

, Habib

, Shamshirband

, Kundi

F.M.

, Habib

, Wang

, Subhan

, Shamshirband

, Asghar

M.Z.

, Ullah

and Habib

, Fuzzy-based sentiment analysis system for analyzing student feedback and satisfaction, Computers, Materials and Continua 62 (2020), 631–655.

95.

Wilson

, Wiebe

and Hoffmann

, Recognizing contextual polarity in phrase-level sentiment analysis, in: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing – HLT ’05, Association for Computational Linguistics, Morristown, NJ, USA, 2005, pp. 347–354.

96.

, Lu

, Su

and Wang

, Chinese Micro-Blog Sentiment Analysis Based on Multiple Sentiment Dictionaries and Semantic Rule Sets, IEEE Access 7 (2019), 183924–183939.

97.

Xing

F.Z.

, Pallucchini

and Cambria

, Cognitive-inspired domain adaptation of sentiment lexicons, Information Processing and Management 56 (2019), 554–564.

98.

, Pan

and Xia

, E-commerce product review sentiment classification based on a naïve Bayes continuous learning framework, Information Processing and Management, (2020), 102221.

99.

Yuan

F.C.

, Lee

C.H.

and Chiu

, Using market sentiment analysis and genetic algorithm-based least squares support vector regression to predict gold prices, International Journal of Computational Intelligence Systems 13 (2020), 234–246.

100.

Yue

, Chen

, Li

, Zuo

and Yin

, A survey of sentiment analysis in social media, Knowledge and Information Systems, (2018), 1–47.

101.

Zafra

S.M.J.

, Valdivia

M.T.M.

, Camara

E.M.

and Lopez

L.A.U.

, Studying the Scope of Negation for Spanish Sentiment Analysis on Twitter, IEEE Transactions on Affective Computing 10 (2015), 129–141.

102.

Zhang

and Gao

, Multi-head attention model for aspect level sentiment analysis, Journal of Intelligent and Fuzzy Systems 38 (2020), 89–96.

GINS: A Global intensifier-based N-Gram sentiment dictionary

Abstract

Keywords

1 Introduction

2 Related work

2.1 Linguistic phenomena

2.1.1 Negators

2.1.2 Intensifiers

2.2 Sentiment dictionaries regarding one or more linguistic phenomena

2.3 Fuzzy logic

3 The proposed method

Table 1 Equal intensifier effect on sentiment words in VADER dictionary Sentiment phrase Score good 0.4404 deeply good 0.4927 very good 0.4927 deeply deeply good 0.5379 very deeply good 0.5379

3.3 Fuzzy pattern extraction of sentiment compounds

4.1 Fuzzy pattern

Footnotes

References

Table 1
Equal intensifier effect on sentiment words in VADER dictionary

Sentiment phrase Score

good 0.4404

deeply good 0.4927

very good 0.4927

deeply deeply good 0.5379

very deeply good 0.5379