A domain-independent data ADHD student model for computer-based educational systems. Data analysis in higher education

Abstract

In traditional learning, teachers can easily have an understanding of how their students work and learn. However, in e-Learning it is more difficult for teachers to monitor how their students behave and learn in the system. As well as to identify if they have any specific awkwardness in their educational process. In this paper, a student model to infer the presence of ADHD symptoms in a Computer-Based Educational System (also known as Learning Management Systems (LMS)) is presented. The student model takes into account two types of students’ characteristics: generic and psychological. Each one is measured through a set of variables, which are correlated to obtain a final profile that can be useful to assist the teaching-learning process. In order to reach this purpose, three Web application tools that collect information about these characteristics have been developed, integrated into a LMS and validated in a case study composed of 30 students (5 suffering from ADHD, 5 that present similar characteristics to ADHD and 20 that supposed do not suffer from ADHD). This case study was carried out through a quantitative research approach and a descriptive scope. Results show that the implemented tools are useful to identify attention problems symptoms in students enrolled in e-learning courses.

Keywords

Inclusive education attention deficit hyperactivity disorder student model e-learning

1. Introduction

UNESCO [32] defines inclusive education as a process intended to respond to students’ diversity by increasing their participation and reducing exclusion within and from education. The challenge posed by greater diversity is to enable students with divergent needs, skills and interests to attain the same high academic standard.

Information and Communication Technologies (ICT) offer the opportunity to respond to the multifaceted individual differences, because they have the potential to create highly versatile educational and training environments that can provide students with equal access to knowledge, regardless of their preferences, diverse learning needs, gender, geographic location, socio-economic or ethnic background, illness or disability, or any other circumstance that would normally hinder the provision of high-quality education. In this context, e-Learning has become an essential tool for teaching large numbers of diverse students because it provides and integrates a wide range of teaching resources and materials (e.g. video, audio, text, subtitles or sign language, multiple languages, and easily understandable expressions), that can be adapted to suit a variety of learning needs and preferences. Among the diversity of students, there are those with ADHD, a lifetime neurobiological and neuropsychological heterogeneous disorder, characterized by inattention, hyperactivity and impulsivity symptoms. This work is centered on young-adult students in a university context. The reasons for focusing this study on this group of people are: a) during the last few years, the number of people diagnosed with ADHD has been increasing [20], b) the research conducted on ADHD is mostly focused on children and adolescents, forgetting young adult and adult population [21], c) several studies have demonstrated that individuals who suffer from this disorder have difficulties and let-downs, such as school and job failures [6], and d) several studies have reported that most students with deficits, such as those that compose the ADHD, who take online courses, drop them in few days because they find the courses hard to follow [17].

In traditional learning, teachers can easily have an understanding of how their students work and learn. However, in e-Learning, it is more difficult for teachers to monitor how individual students behave and learn by using this system and, furthermore, to identify whether a specific student may have a special educational need or not. Adaptive Hypermedia Systems (AHS) is an alternative to the traditional one-size-fits-all approach in the development of hypermedia systems. AHS builds a user model based on the goals, preferences and knowledge of each individual user and, then, uses this constructed model throughout the interaction with the user, in order to adapt the system to the needs of that user [10].

One of the first uses of the AHS was in e-Learning. In this context, the user model is usually called Student Model (SM). Student modelling supports the recognition and monitoring of special needs through building up and updating a SM. Current SMs include a range of information about the students, such as their desired and achieved competences [3,22], learning style [2], cognitive traits [18], personality features preferences [16], learning difficulties [26], among others. To be able to address a student needs in an appropriate way, a reliable SM is necessary; however, getting enough information about a student to create the model is quite challenging.

Based on the above, the objective of this study is to design and implement a SM that considers personal, academic, behavioral and cognitive characteristics to know if an e-Learning student may have ADHD symptoms. The information of each characteristic for a specific student is collected using the registration data on a Learning Management System (LMS) and the results of three computer-based neuropsychological tests designed as web application tools that have been developed and integrated into a LMS. The generated and implemented student- modelling can provide the first step to offer an inclusive learning process to young-adult students with ADHD symptoms. The remainder of the paper is structured as follows: Section 2 provides a background on inclusive e-Learning, student modelling and introduces the target user groups of this study. Section 3 describes our student modeling framework. Section 4 illustrates some study cases to demonstrate the viability of the adopted solution. Finally, Section 5 concludes the paper.

2. Theoretical fundamentals

This section presents the main theoretical basis supporting this research in educational, medical and technological contexts.

2.1. Inclusive e-Learning

The term inclusive education means, essentially, to provide to all students, including those with significant disabilities, the same opportunities and to receive effective educational services, with the necessary supplementary aids and support services, in regular educational classrooms. In this context, legal frameworks, as the Education for All (EFA) policy, led by UNESCO Salamanca Statement [31]; the international declarations, as the Convention on the Rights of Persons with Disabilities [30]; and local legislation, as the Action Plan of inclusive Education (2008/2015) in Catalonia, prohibits discrimination in education and supports inclusive education. Inside the inclusive e-Learning context, it is worth mentioning the terms “Universal Access”, “Universal Design”, and “e-Learning for All” since these are the starting points for an inclusive education system.

Universal Access addresses equitable access and active participation of potentially all citizens in the information society. This is in line with the policy recommendation by the Council of Europe who states that “all who are able and willing to participate successfully in higher education should have fair and equal opportunities to do so” [14]. To make these opportunities viable, design decisions have to be made to assure that a course or a learning environment is accessible for all. This process is called Universal Design” which is defined by the Center for Universal Design at North Carolina State University as “the design of products and environments to be usable by all people. On the other hand, ‘e-Learning for All’ means ensuring that all students, not only the most privileged, acquire knowledge and skills supported by using a computer-based educational system. Thus, individual differences must be considered by ensuring the maximum range and variety of learning opportunities.

In the same direction, the term e-Inclusion arises to refers to all activities that are related to the achievements of inclusive ICTs, as well as the usage of ICTs for inclusion. The major aim of “e-Inclusion” is to reduce the gap between those who have both the access and the capability to use modern information and communication tools and those who don’t, including people in situation of disadvantage due to disabilities or/and those who live in remote regions.

Consequently, inclusive e-Learning, as an area of e-Inclusion, tries to produce inclusive spaces in e-Learning, to consider the best possible special/individual needs and preferences when designing the curriculum (learning purposes, methods and materials, assessment and feedback), but also, when designing the e-Learning applications to support learning. According to the aforementioned factors, “the real value of e-Learning is making training available to people who find it difficult to participate in classroom training, or who choose not to” [19].

Table 1
Common symptoms of ADHD

Categories Description and educational implications

Trouble concentrating and staying focused Difficulties in listening in class, he misses lecture content or homework assignments, lacking of attention to details, making careless mistakes in work, not noticing errors in grammar, punctuation, capitalization, spelling or changes in signs (+, −) in math; difficulties in staying on task and finishing school work; distractible, moving from one uncompleted task to another; lacking of time awareness.

Hyperfocus Tendency to become absorbed in tasks that are stimulating and rewarding. Hyperfocus on a certain subject can cause the student to side-track away from the assigned or important tasks.

Disorganised and forgetful Poor organizational skills, trouble starting and finishing projects (difficulty in getting started on tasks), forgetting appointments, commitments and deadlines frequently, constantly losing or misplacing things (e.g. homework, keys, wallet, phone, documents, bills), difficulty knowing what steps should be taken first, difficulty in organizing thoughts, sequencing ideas, writing essays and planning.

Impulsivity Frequently interrupting others or talking over them. Having poor self-control: blurts out inappropriate thoughts that may be rude regardless of the situation, having addictive tendencies, acting recklessly or spontaneously without thinking about the consequences, having trouble behaving in socially appropriate ways (such as sitting still during a long meeting). Rushing through work, not double checking work, not reading directions, taking short cuts in written work, especially math (does it in his head), hating waiting.

Emotional difficulties Having sense of underachievement, not dealing well with frustration, getting easily flustered and stressed out. Having irritability or mood swings, having trouble staying motivated, hypersensitivity to criticism, short, often explosive, temper, low self-esteem and sense of insecurity. Finding it difficult to activate or arouse themselves to initiate work that must be done, often complaining of being unable to stay alert or even awake in boring situations and frequently seeming to be daydreaming or “in a fog” when they should be more alert, focused and actively engaged in a task.

Hyperactivity or restlessness Feelings of inner restlessness or agitation, tendency to take risks, getting easily bored, having trouble sitting still, constant fidgeting, searching for excitement constantly, talking excessively, doing a lot of random things at once. Showing excessive movement that is not required to complete a specific task.

Categories	Description and educational implications
Trouble concentrating and staying focused	Difficulties in listening in class, he misses lecture content or homework assignments, lacking of attention to details, making careless mistakes in work, not noticing errors in grammar, punctuation, capitalization, spelling or changes in signs (+, −) in math; difficulties in staying on task and finishing school work; distractible, moving from one uncompleted task to another; lacking of time awareness.
Hyperfocus	Tendency to become absorbed in tasks that are stimulating and rewarding. Hyperfocus on a certain subject can cause the student to side-track away from the assigned or important tasks.
Disorganised and forgetful	Poor organizational skills, trouble starting and finishing projects (difficulty in getting started on tasks), forgetting appointments, commitments and deadlines frequently, constantly losing or misplacing things (e.g. homework, keys, wallet, phone, documents, bills), difficulty knowing what steps should be taken first, difficulty in organizing thoughts, sequencing ideas, writing essays and planning.
Impulsivity	Frequently interrupting others or talking over them. Having poor self-control: blurts out inappropriate thoughts that may be rude regardless of the situation, having addictive tendencies, acting recklessly or spontaneously without thinking about the consequences, having trouble behaving in socially appropriate ways (such as sitting still during a long meeting). Rushing through work, not double checking work, not reading directions, taking short cuts in written work, especially math (does it in his head), hating waiting.
Emotional difficulties	Having sense of underachievement, not dealing well with frustration, getting easily flustered and stressed out. Having irritability or mood swings, having trouble staying motivated, hypersensitivity to criticism, short, often explosive, temper, low self-esteem and sense of insecurity. Finding it difficult to activate or arouse themselves to initiate work that must be done, often complaining of being unable to stay alert or even awake in boring situations and frequently seeming to be daydreaming or “in a fog” when they should be more alert, focused and actively engaged in a task.
Hyperactivity or restlessness	Feelings of inner restlessness or agitation, tendency to take risks, getting easily bored, having trouble sitting still, constant fidgeting, searching for excitement constantly, talking excessively, doing a lot of random things at once. Showing excessive movement that is not required to complete a specific task.

2.2. Attention Deficit Hyperactivity Disorder (ADHD)

ADHD is a neurobiological and neuropsychological heterogeneous disorder that, at least in childhood and adolescence, is characterized by inattention, hyperactivity and impulsivity symptoms [4]. In neuropsychological studies performed on people with ADHD, some impairments were found in some of their cognitive functions, specifically failures in “Executive Functions” EF [9,29].

EF has been conceptualized as a term that comprises interrelated higher-order cognitive processes responsible for goal-directed and contextually appropriate behavior [1].

According to Marcheta [23], some of the cognitive and EF areas deficient by the presence of ADHD are: (1) Sustained Attention (SA), which refers to the ability to maintain a stable performance level over a period of time; (2) Working Memory (WM), which is the capacity to store, monitor and manage information; and (3) Verbal Learning (VL), which refers to the capacity to obtain, hold and remind words. Some studies have demonstrated that there is a close relationship between ADHD symptoms and Academic underachievement [5]. Some common symptoms of ADHD adults, grouped into categories and their implication in academy performance are described in Table 1.

2.3. Student Model (SM)

In order to offer inclusive learning applications, learning content or learning paths, which could respond exactly to students’ educational needs and preferences, it is desirable to have information about the student. With this purpose, AHS introduced the concept of SM, which keeps all information about the student. Mainly, this model represents knowledge, interests, preferences, goals, background, and individual traits of the students during their learning process, allowing personalized learning and adaptation towards their current needs [12]. In [24] the SM data is divided into two big groups: 1) The Domain Dependent Data (DDD), referring to the specific knowledge information that the system considers that the user possesses on a particular domain; and 2) The Domain Independent Data (DID) composed of two elements: the Generic Model and the psychological Model of the SM, with an explicit representation.

The generic data is related to the student’s interests, common knowledge and background. The psychological data is related with the cognitive and affective aspects of the student. Some of these characteristics are relevant for a determined type of SM and not for others [11]. Therefore, for each AHS, it will be necessary to define which are the characteristics and relevant parameters of the user to be kept. Based on the aforementioned, we have proposed a SM founded on a DID for detecting ADHD symptoms on e-Learning young adult students.

3. Student Model for detecting indicators of ADHD symptoms on university e-Learning students

3.1. Student Model for inferring ADHD symptoms

An effective SM for our study must be able to recognize if an e-Learning student may have ADHD symptoms. Thus, the research question to be answered in this study is: what characteristics should be evaluated in an e-Learning context in order to detect if university students may have ADHD symptoms?

Based on the theoretical fundamentals presented in Section 2, it is hypothesized that it requires considering at least the following dimension: personal and demographic information; background in clinical, academic and social context; behavioral conduct; and cognitive performance. Table 2 shows all the DID we propose to gather up from the student, for creating the SM, and a detailed description of the data associated to each characteristic dimension is presented. This information is based on the most common characteristics used in SM, according to Martins et al. [25].

Under the proposed model, a dimension which indicates the presence or absence of ADHD symptoms (inheritance of characteristics) was defined. For doing so, the values of the data obtained from the Psychological Model (Behavioral Conduct, Background information and Cognitive Capacities) are related based on a set of classification rules, represented in Fig. 1. In order to define the classification rules, the psychologists in this work suggested that: Behavioral Conduct should present higher significance than Background information and Cognitive Capacities. Based on this, the presence or absence of ADHD symptoms may have one of the following values: Profile 1 means “without ADHD symptoms of ADHD”; profile 2 means “without ADHD symptoms but impairment in executive functions”; profile 3 means “with behavioral symptoms of ADHD”; and profile 4 means “with behavioral and cognitive symptoms of ADHD”.

Before ending the SM explanation, it is important to highlighted that the data of the Generic Model is used in the measures and calculating results of the values of the Psychological Model Data.

In Section 3.2, the implemented system, which includes the used tools to obtain the information from the students for each of the variables of the SM, is presented.

Table 2
Student model based on ADHD symptoms

SM data model Elements Characteristic dimension Data Values Description

Domain Independent Data Generic Model Personal Information First name Student’s first name Data which permit to identify a person

Last name Student’s family name

Email Student’s e-mail address

User (Id) Short name required to log on in the e-Learning platform.

Password Encrypted word required to log on in the e-Learning platform.

Demographic data Birthdate Student’s date of birth (Day/Month/Year) Data which permit to know more about a specific user in terms of location, time, birth

Gender ∙ Female
∙ Male

Nationality Student’s country of birth

City Student’s city of birth

Academic Information Semester 1st, 2nd, 3rd, 4th, 5th, … Data referred to academic level

Level ∙ Associate’ degree
∙ Bachelor’s degree
∙ Technical’ degree
∙ Education Specialist’ degrees

Program Engineering, Musician, Biology, Architecture, Medicine, etc. Referred to the academic program in which the student is enrolled in

Psychological Model Behavioral Conduct ADHD behaviours ∙ Positive
∙ Negative Referred to the results of apply an ADHD behaviour test

Background Clinical history Successful outcome along lifetime (Yes or Not) Referred to the results of apply a history questionnaire

Schools history Good relationships with close family member (Yes or Not)

Familiar and social history Good relationships with friends

Cognitive Capacities Sustained Attention (SA) ∙ Very high
∙ High
∙ Medium
∙ Low
∙ Very low Referred to the performance of the student when presenting tasks which measure cognitive areas

Working Memory (WM)

Verbal Learning (VL)

Inheritance of characteristics Presence or Absence of ADHD symptoms (Diagnostics process) ∙ Profile 1: without ADHD symptoms of ADHD∙ Profile 2: without ADHD symptoms but impairment in executive functions∙ Profile 3: with behavioral symptoms of ADHD∙ Profile 4: with behavioral and cognitive symptoms of ADHD Set of classification rules for determining the presence of ADHD symptoms (see Fig. 1)

SM data model	Elements	Characteristic dimension	Data	Values	Description
Domain Independent Data	Generic Model	Personal Information	First name	Student’s first name	Data which permit to identify a person
Last name	Student’s family name
Email	Student’s e-mail address
User (Id)	Short name required to log on in the e-Learning platform.
Password	Encrypted word required to log on in the e-Learning platform.

Demographic data	Birthdate	Student’s date of birth (Day/Month/Year)	Data which permit to know more about a specific user in terms of location, time, birth
Gender	∙ Female ∙ Male
Nationality	Student’s country of birth
City	Student’s city of birth

Academic Information	Semester	1st, 2nd, 3rd, 4th, 5th, …	Data referred to academic level
Level	∙ Associate’ degree ∙ Bachelor’s degree ∙ Technical’ degree ∙ Education Specialist’ degrees
Program	Engineering, Musician, Biology, Architecture, Medicine, etc.	Referred to the academic program in which the student is enrolled in

Psychological Model	Behavioral Conduct	ADHD behaviours	∙ Positive ∙ Negative	Referred to the results of apply an ADHD behaviour test
Background	Clinical history	Successful outcome along lifetime (Yes or Not)	Referred to the results of apply a history questionnaire
Schools history	Good relationships with close family member (Yes or Not)
Familiar and social history	Good relationships with friends

Cognitive Capacities	Sustained Attention (SA)	∙ Very high ∙ High ∙ Medium ∙ Low ∙ Very low	Referred to the performance of the student when presenting tasks which measure cognitive areas
Working Memory (WM)
Verbal Learning (VL)

	Inheritance of characteristics	Presence or Absence of ADHD symptoms (Diagnostics process)	∙ Profile 1: without ADHD symptoms of ADHD∙ Profile 2: without ADHD symptoms but impairment in executive functions∙ Profile 3: with behavioral symptoms of ADHD∙ Profile 4: with behavioral and cognitive symptoms of ADHD	Set of classification rules for determining the presence of ADHD symptoms (see Fig. 1)

Fig. 1.

Student ADHD profile symptoms.

3.2. Student Modelling System for inferring ADHD symptoms

In the previous section (see Table 1 and Fig. 1), the considered student’s characteristics and the classification rules proposed to create an ADHD profile were described. In this section, the instruments and process used to obtain the information of each characteristic from the student are presented. Additionally, the conducted implementation to integrate these instruments as tools of a LMS, is explained. Figure 2 shows the general framework of the student modelling architecture.

Fig. 2.

General framework of the SM architecture modelling symptoms.

The demographic and academic data, which is part of the Generic Model, is collected through the registration of students in the LMS. On the other hand, information related to the Psychological Model, i.e., Behavioral Conduct, Background and Cognitive Capacities is collected through three external tools that are connected to the LMS. These tools were designed and developed as external web applications in order to connect them to a variety of LMS. A detailed description of each tool is presented in next sub-sections.

The LMS used to implement the complete SM was ATutor, one of the most accessible LMS, available with an open source license. From its beginnings, this LMS was conceived under a user-centered design approach, favoring the attention to the users’ needs and preferences. ATutor adopts the Web Content Accessibility Guidelines (WCAG) for crossing the barriers associated to web content development. Also it is the unique LMS that implements the ISO/IEC 24751-1:2008 standard, which offers the possibility to adjust the system to predefined users’ needs and preferences.

On the other hand, Fig. 2 shows that the set of web applications developed have been connected to the LMS. To embed these applications with ATutor, an inline frame (IFrame) method was used. An IFrame is an HTML document embedded inside another HTML document on a website; in this case, the interactive web applications were embedded in the ATutor webpages. This was complemented using the php5-uuid and php5-curl functions to generate a standard identifier, also known as universally unique identifier (UUID) to enable Web applications and ATutor to uniquely identify information without significant central coordination.

3.2.1. Behavioral Conduct

In order to characterize and to quantify user behaviors that may be relevant to ADHD symptoms, the short version of the Adult ADHD Self-Report Scale (ASRS v1.1) is used [15]. This test consists of six items and each item has five possible answers according with the following Likert scale: never, rarely, sometimes, often and very often. Four or more positive answers suggest the presence of symptoms consistent with ADHD in adults. The result of the evaluation for the behavior conduct is either positive or negative. However, experts in this disorder have stated that even though this scale provides good convergent validity, sensitivity, specificity, and diagnostic capability, there is a high probability of obtaining false-positives. Some of these false-positives are the result of some people with bipolar disorders or schizophrenia, having four or more positive answers. To mitigate this situation, the deTecDAH, an auto-self report questionnaire that aims to evaluate academic, familiar and social situations that may contribute to detect the presence of ADHD symptoms, has been proposed and included in the evaluation process. This questionnaire will be presented in the next section.

3.2.2. Background

In order to complement the characterizing process done by the ASRS questionnaire, the deTecDAH auto-self report questionnaire was designed and implemented. It consists of 17 dichotomous (yes/no) questions related to situations that may occur due to the presence of ADHD. These questions have been organized into three sections: clinical (9 questions), scholar (5 questions) and family/social (3 questions). There were some key questions (5, 2 and 3 respectively) that were used as indicators of the presence of ADHD symptoms in each section. Based on this, about half of key questions answered “yes” indicate the presence of ADHD symptoms (positive), otherwise the result indicates the absence of ADHD symptoms (negative).

3.2.3. Cognitive capacities

Computer-based neuropsychological tests/tasks are frequently used to evaluate the user cognitive performance. We developed a computer-based version of the Sustained Attention Task (SAT) [33] to evaluate the sustained attention area, the Rey’s Auditory Verbal Learning Test (RAVLT) [27], to evaluate the Working Memory (WM) and (3) the Verbal Learning (VL). These tests have been comprised into a neuropsychological battery named eCogniTiDAH. Here, it is important to mention that these tools were developed for research and educative purposes.

The Sustained Attention Task (SAT) The SAT [33] is considered a type of Continuous Performance Test (CPT). It consists of a square with three, four or five dots continuously depicted on the screen. The participant is required to press a button if four dots (target) are presented and not to press the button whenever three or five dots (non-targets) are presented. The performance on this test is measured based on the hits, reaction time and errors, specifically omission and commission errors [8,23]. Hits indicate the number of times a patient was able to detect the stimulus; omission errors indicate the number of times a patient does not press the button when the stimulus appears; commission errors indicate the times that a patient does not react to the stimulus’ presence; and the reaction time indicates the time to respond to a stimulus.

The Rey’s Auditory Verbal Learning Test (RAVLT) RAVLT test [27] consists of fifteen words that are read slowly to the test-taker. Then, the test-taker is required to repeat the words after the reading, independently from the order they were said (A1). The same procedure is repeated in steps A2, A3, A4 and A5, pointing out that the test-taker must always remember all the words, including those said previously. Then, a second list of words (B1) is read as a distractor, and the subject must recall only these new words. After that, the test-taker is asked for the words of the first list (A6). Twenty-five minutes later, the test-taker must able to recall the words of the first list (A7) in order to assess the delayed recall of episodic memory. Word production on the first trial was included as a measure of short-term memory or working memory; word production on trials 1, 2, 3, 4 and 5 as an index of the learning curve; delayed recall and retention score.

4. Study case

The study case was carried out through a quantitative research approach with a descriptive scope. This scope of research pursues to specify important properties of individuals, groups, communities or any other phenomenon that is subjected to analysis [13] and it is precisely the goal of this study, to describe the variables of the participant associated to ADHD symptoms inferred using the user modelling framework tested, and compare the results with normalized data.

4.1. Participants

The study case was implemented with students from the Manuela Beltran University (UMB) in Colombia. Specifically, 30 university young students were included in the study distributed as follow: 5 young students diagnosed with ADHD (ADHD+, $n = 5$ ), 5 young students referred for attention problems due to ADHD symptomatology but not diagnosed as such (ADHD−, $n = 5$ ), and 20 healthy young students (HYS, $n = 20$ ). The participants of the (ADHD+) and (ADHD−) groups were referred by the University Welfare Department of the UMB, all of them belong to different university programs. The inclusion criteria were: to be aged from 18 to 30 and have sufficient capacity to provide and sign the corresponding informed consent. Exclusion criteria for all group included: not having available time for taking the test and current drug and alcohol use. ADHD+ and ADHD− participants taking medication for ADHD were not excluded.

4.2. Procedures

Two psychology professors at the UMB together with the project staff conducted the study case. Professors were previously trained in the use of the system, including the ASRS, deTecDAH, eCogniTiDAH tools.

Students received the guidelines to participate in the study and were trained to fill out the questionnaires and cognitive tasks by the teachers. In line with ethical principles for research, each student provided informed consent for participation in the study in written form.

During the process students’ data were recorded on ATutor, thus getting the sociodemographic information that is required for the Generic Model. Once registered, the students were able to access the Psychological Model. In order not to exhaust or bore the participants, the test was divided in two sections. In the first one, the short version of Adult ADHD Self-Report Scale (ASRS v1.1) and the deTecDAH auto-self report questionnaire were administered. In the second one, the eCogniTiDAH neuropsychological battery was complete. The break time between sections was two hours. The students were individually tested in a noise isolated room.

4.3. Data analysis and results

The results presented below describe the student variables in the SM inferred by the system. The analysis was performed by groups (ADHD+, ADHD− and HYS) to finally draw conclusions.

Regarding the Generic Model, the information is represented in Table 3.

Table 3
Participants characteristics

Characteristic ADHD+ ADHD− HYS

Media Age 21.4 20.6 19.75

Gender Women 1 2 13

Men 4 3 7

Medication 3 0 0

Academic level I 2 3 10

II 3 2 8

III 0 0 2

Academic program

– Psychology 3 2 2

– Criminology 2 1 2

– Sports science 2 7

– Physiotherapy 5

– Nursing 2

– Law 2

Characteristic	ADHD+	ADHD−	HYS
Media Age	21.4	20.6	19.75
Gender	Women	1	2	13
Men	4	3	7
Medication	3	0	0
Academic level	I	2	3	10
II	3	2	8
III	0	0	2
Academic program
– Psychology	3	2	2
– Criminology	2	1	2
– Sports science		2	7
– Physiotherapy			5
– Nursing			2
– Law			2

In relation to the results shown in Table 3, the average age at ADHD+ and ADHD− group is higher compared to the average of the other two groups and the academic level of the three groups is mostly I and II. This result is consistent with the theoretical foundations that state that students with ADHD tend to repeat school years [34] which means that the student will apply to the university with a higher age than students without ADHD do. On the other hand, the 80% of students in the ADHD+ group were men, this is recurrent with several studies, indicating that men suffer more from the disorder than women [7].

Regarding the Psychological Model, the first dimension evaluated was the Behavior Conduct using the Adult ADHD Self-Report Scale (ASRS v1.1). Tables 4, 5 and 6 present the obtained results for ADHD+, ADHD− and HYS groups respectively.

According to the results shown in Table 4, the ASRS is in line with the previous diagnosis of the students included in the ADHD+ group. Additionally, it is important to highlight that all students who have not been previously diagnosed with ADHD (see Tables 5 and 6) have obtained a positive result, which may show the necessity of complementing the assessment with other information. It may also indicate an under diagnosis of ADHD.

Table 4

Behavior conduct results for ADHD+ group

Student	ASRS result
1	Positive
2	Positive
3	Positive
4	Positive
5	Positive

Table 5

Behavior conduct results for ADHD− group

Student	ASRS result
6	Positive
7	Positive
8	Positive
9	Positive
10	Positive

Table 6

Behavior conduct results for HYS group

Student	ASRS result
11	Positive
12	Negative
13	Negative
14	Negative
15	Positive
16	Positive
17	Negative
18	Negative
19	Negative
20	Positive
21	Negative
22	Positive
23	Negative
24	Negative
25	Negative
26	Negative
27	Positive
28	Negative
29	Negative
30	Negative

Table 7

Background results for ADHD+ group

Student	Clinical (5)	Scholar (2)	Familiar-social (3)	Total (10)	Background result
1	5	1	3	9	Positive
2	5	2	2	9	Positive
3	5	2	1	8	Positive
4	5	2	1	8	Positive
5	5	2	2	9	Positive

Table 8

Background results for ADHD− group

Student	Clinical (5)	Scholar (2)	Familiar-social (3)	Total (10)	Background result
6	3	1	1	5	Positive
7	3	1	2	6	Positive
8	2	2	1	5	Positive
9	4	2	1	7	Positive
10	3	2	1	6	Positive

Table 9

Background results for HYS group

Student	Clinical (5)	Scholar (2)	Familiar-social (3)	Total (10)	Background result
11	0	1	0	1	Negative
12	0	1	0	1	Negative
13	0	2	0	2	Negative
14	0	2	0	2	Negative
15	1	2	1	4	Negative
16	0	1	0	1	Negative
17	0	1	0	1	Negative
18	0	2	0	2	Negative
19	0	2	0	2	Negative
20	0	2	0	2	Negative
21	1	1	0	2	Negative
22	0	1	0	1	Negative
23	1	2	1	4	Negative
24	0	2	0	2	Negative
25	0	2	0	2	Negative
26	1	1	0	2	Negative
27	0	1	0	1	Negative
28	0	2	1	3	Negative
29	2	2	1	5	Positive
30	0	2	0	2	Negative

The other dimension considered in the Psychological Model was the Background of the student in clinical, educational and familiar-social contexts using the deTecDAH auto-self report questionnaire. Results of this evaluation are presented in Tables 7, 8 and 9 according to the number of affirmative responses to the key questions (5, 2 and 3 respectively). A positive result in the Background is obtained when the value of the add of the number of affirmative responses in the clinical, the scholar and the familiar-social context is 5 or greater.

By comparing Background results with the ASRS, it can be noted that the students of the ADHD+ and ADHD− groups maintained their positive outcome, while the number of student that obtained a positive outcome in the HYS decreased. This difference can be explained by the fact that deTecDAH have several questions related to the clinical context.

Concerning the cognitive dimension using eCogniTiDAH, it is important to describe that, generally, statistics are used to define the performance of a patient in these kind of tests. We compare students results with the normalized data, according to age and education level, of people without cognitive problems on each of the three tests [27,33]. Considering that we have different evaluation scales for each test, we compare the patient results on each of them with the mean (μ) of its normalized data in terms of its standard deviation (α). Table 10 gives the parameters that classify the students’ results. Those parameters are based on experienced psychologist in ADHD field.

Table 10

Students’ results per each test

Statistic	Student result	Assigned value
Below $μ - 2 σ$	Very Low	1
Between $μ - 2 σ$ and $μ - σ$	Low	2
Between $μ - σ$ and $μ + σ$	Medium	3
Between $μ + σ$ and $μ + 2 σ$	High	4
Above $μ + 2 σ$	Very High	5

However, normalized data for the SAT and RAVLT consistent to the population and properties required on this research was not found. To address this, we normalized student data to control group means obtained with the respective results of our version of the test.

Furthermore, as a variety of characteristics of the cognition it has been considered to extract information about the cognitive performance of a student, it might be said that the cognitive trait dimension comprises a student model itself; thus, for the final cognitive performance result, a number from 1 to 5 is assigned for the possible results on each of the three tools. The final SA result is obtained by adding the values found in these tests. The scale for the classification of the final cognitive performance is shown in Table 11.

As sown in Table 11, the possible results of the Cognitive Capacities are: Very High, High, Medium, Low and Very Low. The ranges for the final classification are obtained considering the limits of the possible results, for example, two very low results (2 × 1) and one low (2) should produce a final very low one (4), but two low results (2 × 2) and one very low (1) should produce a final low result (5). The rest of the ranges are constructed in the same way.

Having explained this, the results of the assessment of each area considered in the cognitive dimension are presented. The first area evaluated was ‘Sustained Attention’ (SA), Tables 12, 13 and 14 shows results for each student.

Table 11

Range for final cognitive performance classification

Ranges	Classification
{3, 4}	Very Low
{5, 6, 7}	Low
{8, 9, 10}	Medium
{11, 12, 13}	High
{14, 15}	Very High

Table 12

Sustained Attention (SA) results for ADHD+ group

Student	Hit	Omission errors	Error commission	Reaction time	Final SA result
1	Low	Low	Medium	Medium	Low
2	Low	Low	Low	Low	Low
3	Medium	Medium	Medium	Low	Medium
4	Medium	Medium	Medium	Low	Medium
5	Medium	Medium	Medium	Low	Medium

Table 13

Sustained Attention (SA) results for ADHD− group

Student	Hit	Omission errors	Error commission	Reaction time	Final SA result
6	Low	Low	Medium	Low	Low
7	Low	Medium	Medium	Low	Medium
8	Medium	Medium	Medium	Medium	Medium
9	Medium	Medium	Medium	Medium	Medium
10	Medium	Medium	Medium	Medium	Medium

Table 14

Sustained Attention (SA) results for HYS group

Student	Hit	Omission errors	Error commission	Reaction time	Final SA result
11	Very high	High	High	High	High
12	Medium	Medium	Medium	High	Medium
13	High	High	High	High	High
14	Medium	Medium	Medium	High	Medium
15	Low	Low	Medium	Medium	Low
16	High	High	High	High	High
17	High	High	High	High	High
18	Very low	Low	Medium	Low	Low
19	High	High	High	High	High
20	Medium	Medium	Medium	Medium	Medium
21	High	High	High	High	High
22	Medium	Medium	Medium	Medium	Medium
23	Low	Medium	Low	Low	Low
24	Medium	Medium	Medium	Medium	Medium
25	Medium	Medium	High	High	Medium
26	Medium	Medium	Medium	High	Medium
27	Medium	Medium	Medium	High	Medium
28	High	High	High	High	High
29	Very low	Medium	Low	Low	Low
30	Medium	Medium	High	High	Medium

To better assess the Sustained Attention results, these have been grouped into the number of times that a certain result was obtained. Table 15 shows SA global results.

Table 15

Sustained Attention (SA) global results

Student	Hit	Omission errors	Error commission	Reaction time	Final SA result
ADHD+
Low	2	2	1	4	2
Medium	3	3	4	1	3
ADHD−
Low	2	1	0	2	2
Medium	3	4	5	3	3
HYS
Very low	2	0	0	0	0
Low	2	2	2	3	4
Medium	9	11	9	4	9
High	6	7	9	13	7
Very high	1	0	0	0	0

According to R and M Scandar [28] the Hits and the Omission Errors provide information about the attention quality, but the last one is a more meaningful measure. Based on Table 15, it is important to note that in the Hits performance of the ADHD+ and ADHD− groups predominates the Low and Medium, while there is not a marked predominance in the HYS group. However, in HYS group the results show High and Very High performances, cases that are not observable in the other two groups.

On the other hand, the results of the Omission Errors in the ADHD+ and ADHD− groups have the same predominance (Medium), while the performance in the HYS group improved: Low performance decreased and the Medium and High increased. Referring to these findings, it could be inferred that attentional quality in the HYS group is greater.

According to the Error Commission, R and M Scandar [28], state that these indicate poor inhibitory control, process that is deficient in people with ADHD. As it can be seen in Table 15, the Error Commission performance of the ADHD+ and ADHD− groups, tends to Medium, while in the HYS there is the same percentage of Medium and High but there is a small percentage of Low.

About the Reaction Time it is important to note that the lower performance of the ADHD+ and ADHD− groups was obtained in this measure. Additionally, the Reaction Time yielded the most marked difference by comparing the results of the three groups, which means that it could be a decisive measure for inferring ADHD symptoms.

As regard to the final SA Result field, which is calculated by averaging the Hit, the Omission Error, the Commission Error and the Reaction Time results, given greater weight to the Omission Error in case of ties, the behavior of the results is congruent with those obtained in the other measures.

Regarding Working Memory and Verbal Learning, the values considered for this analysis was the number of word production. As mentioned in Section 2, results on the first trial are included as a measure of Working Memory. These results are presented in Tables 16, 17 and 18.

Table 16

Working Memory (WM) results for ADHD+ group

Student	WM result
1	Low
2	Low
3	Very Low
4	Low
5	Very Low

Table 17

Working Memory (WM) results for ADHD− group

Student	WM result
6	Very Low
7	Low
8	Medium
9	Medium
10	Low

Table 18

Working Memory (WM) results for HYS group

Student	WM result
11	Very Low
12	Medium
13	Medium
14	Medium
15	Low
16	Medium
17	Medium
18	Medium
19	Medium
20	Low
21	Medium
22	Medium
23	High
24	Medium
25	Medium
26	Medium
27	Medium
28	Medium
29	Low
30	Medium

As it can be seen in Table 16, the Low performance is the tendency in the ADHD+ group. These results are in line with the ones on the prior evaluation.

On the other hand, there is not a marked tendency in the ADHD− group (see Table 17), although the results include Low and Very Low performances which corresponds to the expected result, given that the students in this group were refereed by the university welfare department as students with potential ADHD problems.

The results of the HYS group (see Table 18) show a clear tendency to Medium performance, even though High, Low and Very low were obtained. These can be looked as good results, given that the population included in this group were considered with no ADHD, but anyone could suffer from it.

In Tables 19, 20 and 21 the results of the trial 2, 3, 4 and 5 are presented as an index of Verbal Learning.

Table 19 shows a Low and Very low performance as a tendency in the ADHD+ group, while in the ADHD− group (Table 20) there is room for Medium performances. On the other hand, in Table 21 there is a clear tendency in the HYS group to the Medium performance, even though High, Low and Very low performances were obtained.

Table 19

Verbal Learning (VL) results for ADHD+ group

Student	T 2	T 3	T 4	T 5	T 6	Final VL
1	L	L	L	L	L	L
2	L	L	L	L	L	L
3	VL	VL	VL	VL	VL	VL
4	L	L	L	L	L	L
5	VL	VL	VL	VL	VL	VL

Table 20

Verbal Learning (VL) results for ADHD− group

Student	T 2	T 3	T 4	T 5	T 6	Final VL
6	VL	VL	VL	VL	VL	VL
7	L	L	L	L	L	L
8	M	M	L	L	L	L
9	L	M	M	L	L	L
10	L	L	L	L	L	L

Table 21

Verbal Learning (VL) results for HYS group

Student	T 2	T 3	T 4	T 5	T 6	Final VL
11	VL	VL	VL	VL	VL	VL
12	M	M	M	M	M	M
13	M	M	M	M	M	M
14	M	M	M	M	M	M
15	L	L	L	L	L	Low
16	M	M	M	M	M	M
17	M	M	M	M	M	M
18	M	M	M	M	M	M
19	M	M	M	M	M	M
20	L	L	L	L	L	L
21	M	M	M	M	M	M
22	M	M	M	M	M	M
23	H	H	H	H	H	H
24	M	M	M	M	M	M
25	M	M	M	M	M	M
26	M	M	M	M	M	M
27	M	M	M	M	M	M
28	M	M	M	M	M	M
29	L	L	L	L	L	L
30	M	M	M	M	M	M

Because of the complexity of the cognitive dimension, a Final Cognitive performance was inferred relating the Sustained Attention, the Working Memory and the Verbal Learning performance. These results are obtained adding the values found and applying a classification explained in Table 7. These final results are presented in Tables 22, 23 and 24.

Table 22

Final cognitive results for ADHD+ group

Student	Sustained Attention	Working Memory	Verbal Learning	Final result
1	Low	Low	Low	Low
2	Low	Low	Low	Low
3	Medium	Very low	Very low	Low
4	Medium	Low	Low	Low
5	Medium	Very low	Very low	Low

Table 23

Final cognitive results for ADHD− group

Student	Sustained Attention	Working Memory	Verbal Learning	Final result
6	Low	Very low	Very low	Very low
7	Low	Low	Low	Low
8	Medium	Medium	Low	Medium
9	Medium	Medium	Low	Medium
10	Medium	Low	Low	Low

Table 24

Final cognitive results for HYS group

Student	Sustained Attention	Working Memory	Verbal Learning	Final result
ADHD+
1	Low	Low	Low	Low
2	Low	Low	Low	Low
3	Medium	Very low	Very low	Low
4	Medium	Low	Low	Low
5	Medium	Very low	Very low	Low
ADHD−
6	Low	Very low	Very Low	Very low
7	Low	Low	Low	Low
8	Medium	Medium	Low	Medium
9	Medium	Medium	Low	Medium
10	Medium	Low	Low	Low
HYS
11	High	Very low	Very low	Low
12	Medium	Medium	Medium	Medium
13	High	Medium	Medium	Medium
14	Medium	Medium	Medium	Medium
15	Low	Low	Low	Low
16	High	Medium	Medium	Medium
17	High	Medium	Medium	Medium
18	Low	Medium	Medium	Medium
19	High	Medium	Medium	Medium
20	Medium	Low	Low	Low
21	High	Medium	Medium	Medium
22	Medium	Medium	Medium	Medium
23	Low	High	High	Medium
24	Medium	Medium	Medium	Medium
25	Medium	Medium	Medium	Medium
26	Medium	Medium	Medium	Medium
27	Medium	Medium	Medium	Medium
28	High	Medium	Medium	Medium
29	Low	Low	Low	Low
30	Medium	Medium	Medium	Medium

As it can be seen in Tables 22, 23 and 24 the final result is similar to the performance obtained by the students in each cognitive area.

Table 25

ADHD+ student profile

Student	Results			Profile
1	Positive	Positive	Low	4
2	Positive	Positive	Low	4
3	Positive	Positive	Low	4
4	Positive	Positive	Low	4
5	Positive	Positive	Low	4

Table 26

ADHD− student profile

Student	Results			Profile
6	Positive	Positive	Very Low	4
7	Positive	Positive	Low	4
8	Positive	Positive	Medium	3
9	Positive	Positive	Medium	3
10	Positive	Positive	Low	4

Table 27

HYS student profile

Student	Results			Profile
11	Positive	Negative	Low	4
12	Negative	Negative	Medium	1
13	Negative	Negative	Medium	1
14	Negative	Negative	Medium	1
15	Positive	Positive	Low	4
16	Positive	Negative	Low	4
17	Negative	Negative	Medium	1
18	Negative	Negative	Medium	1
19	Negative	Negative	Medium	1
20	Positive	Negative	Low	4
21	Negative	Negative	Medium	1
22	Positive	Negative	Medium	3
23	Negative	Negative	Medium	1
24	Negative	Negative	Medium	1
25	Negative	Negative	Medium	1
26	Negative	Negative	Medium	1
27	Positive	Negative	Medium	3
28	Negative	Negative	Medium	1
29	Negative	Positive	Low	2
30	Negative	Negative	Medium	1

Conversely, Tables 25, 26 and 27 show the results of the profile of each student according to ADHD when applying the classification rules that were proposed.

Table 25 shows that all the five students in the ADHD+ group were classified in profile 4, which means “behavioral and cognitive symptoms of ADHD”.

Table 26 shows that three students of the ADHD− were classified in the profile 4 and two students in the profile 3, this last profile means “behavioral symptoms of ADHD”.

Finally, Table 27 shows that thirteen students of the HYS were classified in the profile 1, which means “without ADHD symptoms of ADHD”; one student in the profile 2, which means “without ADHD symptoms but impairment in executive functions”; three in the profile 3; and three in profile 4.

This classification shows that it was possible to infer an ADHD profile to each student, based on the student results in each dimension considered in the UM proposed. These results are important because they support the purpose of detecting ADHD symptoms in e-Learning.

5. Conclusions and future work

e-Learning has become an essential tool for the teaching of large numbers of diverse students. The overall goal behind this work is to provide quality learning processes to university students with ADHD, who have found in e-Learning an alternative to access academic training. In this context, the first step to respond to the educational needs that this disorder involves, consists in identifying if an e-Learning student may have ADHD symptoms.

The study presented in this paper evidenced the possibility of doing the identification of the symptoms through the definition of a SM and the implementation of a Student Modelling System. Results of the evaluation prove that the system is able to make a profile of the students with symptoms of ADHD, based on the characteristics included in the UM.

The study is not intending to present a method for detecting ADHD in a medical context, but can support teachers and trainers in an educational context, giving them insights about possible symptoms of ADHD in their students that can be corroborated by psychologists.

The research provides solid bases to offer educational processes that recognize preferences and needs of e-Learning students that have ADHD. On the other hand, it facilitates a personalized and adapted education to students, due to the knowledge the system acquires of them over time.

Future work will be mainly focused on enriching the dataset and balancing each group in terms of gender in order to improve the validity of results and also allow for a wider variety of factors and influences to be studied. Among other initiatives, this will mean to contact others universities where a case study could be implemented.

On the other hand, work is undertaken to develop learning resources and to design teaching strategies to offer a better learning experience to university students suffering from ADHD and a rewarding teaching experience to teachers of these students.

Footnotes

Acknowledgements

This work was supported in part by the Spanish Science and Education Ministry through the Open Co-Creation Project under Grant TIN2014-53082-R, and in part by the Comunicacions i Sistemes Distribuïts Project through the University of Girona 2016-2018 under Grant MPCUdG2016.

References

J.A.

Alvarez and

Emory, Executive function and the frontal lobes: A meta-analytic review, Neuropsychology Review16 (2006), 17–42. doi:10.1007/s11065-006-9002-x.

Baldiris,

Fabregat and

Graf, Dynamic user modeling and adaptation based on learning styles for supporting semi-automatic generation of IMS learning design, in: IEEE International Conference on Advanced Learning Technologies, 2011.

S.M.

Baldiris,

O.C.

Santos,

Huerva,

Fabregat and

J.G.

Boticario, Multidimensional adaptations for open learning management systems, in: International Conference on Web Intelligence and Intelligent Agent Technology, 2008.

R.A.

Barkley, Attention-Deficit/Hyperactivity Disorder: A Handbook for Diagnosis and Treatment, The Guilford Press, New York, 1998.

Barry,

Lyman and

Grofer, Academic underachievement and attention-deficit/hyperactivity disorder: The negative impact of symptom severity on school performance, Journal of School Psychology40 (2002), 259–283. doi:10.1016/S0022-4405(02)00100-0.

Biederman and

Faraone, Attention-deficit hyperactivity disorder, The Lancet367 (2005), 237–248. doi:10.1016/S0140-6736(05)66915-2.

Biederman,

S.V.

Faraone,

Braten,

Doyle,

Spenceret al., Influence of gender on attention deficit hyperactivity disorder on children referred to a psychiatric clinic, American Journal of Psychiatry159 (2002), 36–42. doi:10.1176/appi.ajp.159.1.36.

Börger

et al., Heart rate variability and sustained attention in ADHD children, Journal of Abnormal Child Psychology27 (1999), 32–33.

T.E.

Brown, DSM-IV: ADHD and executive function impairments, Advanced Studies in Medicine2 (2002), 910–914.

10.

Brusilovsky, Methods and techniques of adaptive hypermedia, User Modeling and User Adapted Interaction6 (1996), 87–129. doi:10.1007/BF00143964.

11.

Brusilovsky, Adaptive hypermedia, Journal User Modeling and User-Adapted Interaction11 (2001), 87–110. doi:10.1023/A:1011143116306.

12.

Brusilovsky and

Millán, User models for adaptive hypermedia and adaptive educational systems, in: The Adaptive Web, Springer-Verlag, Berlin, 2007, pp. 3–53. doi:10.1007/978-3-540-72079-9_1.

13.

Cid,

Méndez and

Sandoval, Investigación Fundamentos y Metodología, Prentice Hall, México, 2011.

14.

Council of Europe, Recommendation No. R (98) 3 on access to higher education in Europe.

15.

Daigre

et al., Adult ADHD Self-Report Scale (ASRSv1.1) symptom checklist in patients with substance use disorders, Actas españolas de psiquiatría37 (2009), 299–305.

16.

El Bachari,

E.H.

Abdelwahed and

El Adnani, Design of an adaptive e-learning model based on learner’s personality, Ubiquitous Computing and Communication Journal5 (2010).

17.

Grabinger, A framework for supporting postsecondary learners with psychiatric disabilities in online environments, Electronic Journal of e-Learning8 (2010), 101–110.

18.

Graf,

Lin and Kinshuk , The relationship between learning styles and cognitive traits – getting additional information for improving student modelling, Computers in Human Behavior24 (2008), 122–137. doi:10.1016/j.chb.2007.01.004.

19.

Grober,

Weicht and

Berg, Inclusive eLearning–special needs and special solutions?, in: 3rd Workshop on Inclusive eLearning, 2010.

20.

R.C.

Kessler

et al., The prevalence and correlates of adult ADHD in the United States: Results from the national comorbidity survey replication, American Journal of Psychiatry163 (2006), 716–723. doi:10.1176/ajp.2006.163.4.716.

21.

Kroes

et al., Child psychiatric diagnoses in a population of Dutch school-children aged 6 to 8 years, Journal of the American Academy of Child and Adolescent Psychiatry40 (2001), 1401–1409. doi:10.1097/00004583-200112000-00010.

22.

Mancera,

Baldiris and

Fabregat, Modelling collaborative competence level using machine learning techniques, in: International Conference e-Learning (IADIS), 2008.

23.

N.D.

Marchetta, Cognitive Processes in Adults with ADHD, Neuropsych Publishers, Maastricht, 2007. ISBN 978-90-75578-35-2.

24.

A.C.

Martins,

Faria,

Vaz de Carvalho and

Carrapatoso, User modeling in adaptive hypermedia educational systems, Educational Technology & Society11 (2008), 194–207.

25.

A.C.

Martins,

Faria,

Vaz de Carvalho and

Carrapatoso, User modeling in adaptive hypermedia educational systems, Educational Technology & Society11 (2008), 194–207.

26.

Mejía,

Diaz,

J.E.

Jimenez and

Fabregat, Considering cognitive traits of university students with dyslexia in the context of a learning management system, in: Foundations of Augmented Cognition. Directing the Future of Adaptive Systems,

D.D.

Schmorrow and

C.M.

Fidopiastis, eds, 2011, Vol. 6780, pp. 432–441. doi:10.1007/978-3-642-21852-1_50.

27.

Rey, L’Examen Clinique in Psychologie, Press Universitaire de France, Paris, 1958.

28.

Scandar and

Scandar, Test de atención sostenida, Software.

29.

Seidman, Neuropsychological functioning in people with ADHD across the lifespan, Clinical Psychology Review103 (2006), 403–428.

30.

UN Nations, Convention on rights of persons with disabilities, 2009.

31.

UNESCO, The Salamanca statement and framework for action on special needs education, in: World Conference on Special Needs Education: Access and Quality, 1994.

32.

UNESCO, Guidelines for Inclusion: Ensuring Access to Education for All, Paris, 2005. Available at http://unesco.org/educacion/inclusive.

33.

Van der Elst,

M.P.J.

Van Boxtel,

G.J.P.

Van Breukelen and

Jolles, The concept shifting test: Adult normative data, psychological assessment, The American Psychological Association18 (2006), 424–432.

34.

Zambrano, Académico en Escolares con Déficit de Atención/hiperactividad en una Muestra de colegios de la Ciudad de Bogotá, 2013.