Perspectives on Psychological Science

Research on clinical versus statistical prediction has demonstrated that algorithms make more accurate predictions than humans in many domains. Geopolitical forecasting is an algorithm-unfriendly domain, with hard-to-quantify data and elusive reference classes that make predictive model-building difficult. Furthermore, the stakes can be high, with missed forecasts leading to mass-casualty consequences. For these reasons, geopolitical forecasting is typically done by humans, even though algorithms play important roles. They are essential as aggregators of crowd wisdom, as frameworks to partition human forecasting variance, and as inputs to hybrid forecasting models. Algorithms are extremely important in this domain. We doubt that humans will relinquish control to algorithms anytime soon—nor do we think they should. However, the accuracy of forecasts will greatly improve if humans are aided by algorithms.

Artificial intelligence (AI) has the potential to improve human decision-making by providing decision recommendations and problem-relevant information to assist human decision-makers. However, the full realization of the potential of human–AI collaboration continues to face several challenges. First, the conditions that support complementarity (i.e., situations in which the performance of a human with AI assistance exceeds the performance of an unassisted human or the AI in isolation) must be understood. This task requires humans to be able to recognize situations in which the AI should be leveraged and to develop new AI systems that can learn to complement the human decision-maker. Second, human mental models of the AI, which contain both expectations of the AI and reliance strategies, must be accurately assessed. Third, the effects of different design choices for human-AI interaction must be understood, including both the timing of AI assistance and the amount of model information that should be presented to the human decision-maker to avoid cognitive overload and ineffective reliance strategies. In response to each of these three challenges, we present an interdisciplinary perspective based on recent empirical and theoretical findings and discuss new research directions.

On digital media, algorithms that process data and recommend content have become ubiquitous. Their fast and barely regulated adoption has raised concerns about their role in well-being both at the individual and collective levels. Algorithmic mechanisms on digital media are powered by social drivers, creating a feedback loop that complicates research to disentangle the role of algorithms and already existing social phenomena. Our brief overview of the current evidence on how algorithms affect well-being, misinformation, and polarization suggests that the role of algorithms in these phenomena is far from straightforward and that substantial further empirical research is needed. Existing evidence suggests that algorithms mostly reinforce existing social drivers, a finding that stresses the importance of reflecting on algorithms in the larger societal context that encompasses individualism, populist politics, and climate change. We present concrete ideas and research questions to improve algorithms on digital platforms and to investigate their role in current problems and potential solutions. Finally, we discuss how the current shift from social media to more algorithmically curated media brings both risks and opportunities if algorithms are designed for individual and societal flourishing rather than short-term profit.

It is critical to understand how algorithms structure the information people see and how those algorithms support or undermine society’s core values. We offer a normative framework for the assessment of the information curation algorithms that determine much of what people see on the internet. The framework presents two levels of assessment: one for individual-level effects and another for systemic effects. With regard to individual-level effects we discuss whether (a) the information is aligned with the user’s interests, (b) the information is accurate, and (c) the information is so appealing that it is difficult for a person’s self-regulatory resources to ignore (“agency hacking”). At the systemic level we discuss whether (a) there are adverse civic-level effects on a system-level variable, such as political polarization; (b) there are negative distributional or discriminatory effects; and (c) there are anticompetitive effects, with the information providing an advantage to the platform. The objective of this framework is both to inform the direction of future scholarship as well as to offer tools for intervention for policymakers.

Most content consumed online is curated by proprietary algorithms deployed by social media platforms and search engines. In this article, we explore the interplay between these algorithms and human agency. Specifically, we consider the extent of entanglement or coupling between humans and algorithms along a continuum from implicit to explicit demand. We emphasize that the interactions people have with algorithms not only shape users’ experiences in that moment but because of the mutually shaping nature of such systems can also have longer-term effects through modifications of the underlying social-network structure. Understanding these mutually shaping systems is challenging given that researchers presently lack access to relevant platform data. We argue that increased transparency, more data sharing, and greater protections for external researchers examining the algorithms are required to help researchers better understand the entanglement between humans and algorithms. This better understanding is essential to support the development of algorithms with greater benefits and fewer risks to the public.

Even though social media platforms have created opportunities for more efficient and convenient civic participation, they are unlikely to bring about social change if the online actions do not propagate to offline civic participation. This article begins by reviewing the meta-analytic evidence on the relation between social media use and offline civic participation. Following this discussion, we present a theoretical framework that incorporates the attitudinal, motivational, and relational processes that may mediate the effect of social media use on offline civic participation. The framework highlights how social media algorithms may shape attitudes on important societal issues, promote generalized action goals among habitual users, and build social capital. We further discuss factors that may strengthen or undermine each of these processes, suggest ways to design and implement algorithms that may promote offline civic participation, and propose questions for future research.

Recent studies have documented the type of content that is most likely to spread widely, or go “viral,” on social media, yet little is known about people’s perceptions of what goes viral or what should go viral. This is critical to understand because there is widespread debate about how to improve or regulate social media algorithms. We recruited a sample of participants that is nationally representative of the U.S. population (according to age, gender, and race/ethnicity) and surveyed them about their perceptions of social media virality (n = 511). In line with prior research, people believe that divisive content, moral outrage, negative content, high-arousal content, and misinformation are all likely to go viral online. However, they reported that this type of content should not go viral on social media. Instead, people reported that many forms of positive content—such as accurate content, nuanced content, and educational content—are not likely to go viral even though they think this content should go viral. These perceptions were shared among most participants and were only weakly related to political orientation, social media usage, and demographic variables. In sum, there is broad consensus around the type of content people think social media platforms should and should not amplify, which can help inform solutions for improving social media.

Technological innovations have become a key driver of societal advancements. Nowhere is this more evident than in the field of machine learning (ML), which has developed algorithmic models that shape our decisions, behaviors, and outcomes. These tools have widespread use, in part, because they can synthesize massive amounts of data to make seemingly objective recommendations. Yet, in the past few years, the ML community has been drawing attention to the need for caution when interpreting and using these models. This is because these models are created by humans, from data generated by humans, whose psychology allows for various biases that impact how the models are developed, trained, tested, and interpreted. As psychologists, we thus face a fork in the road: Down the first path, we can continue to use these models without examining and addressing these critical flaws and rely on computer scientists to try to mitigate them. Down the second path, we can turn our expertise in bias toward this growing field, collaborating with computer scientists to reduce the models’ deleterious outcomes. This article serves to light the way down the second path by identifying how extant psychological research can help examine and curtail bias in ML models.

We illustrate how standard psychometric inventories originally designed for assessing noncognitive human traits can be repurposed as diagnostic tools to evaluate analogous traits in large language models (LLMs). We start from the assumption that LLMs, inadvertently yet inevitably, acquire psychological traits (metaphorically speaking) from the vast text corpora on which they are trained. Such corpora contain sediments of the personalities, values, beliefs, and biases of the countless human authors of these texts, which LLMs learn through a complex training process. The traits that LLMs acquire in such a way can potentially influence their behavior, that is, their outputs in downstream tasks and applications in which they are employed, which in turn may have real-world consequences for individuals and social groups. By eliciting LLMs’ responses to language-based psychometric inventories, we can bring their traits to light. Psychometric profiling enables researchers to study and compare LLMs in terms of noncognitive characteristics, thereby providing a window into the personalities, values, beliefs, and biases these models exhibit (or mimic). We discuss the history of similar ideas and outline possible psychometric approaches for LLMs. We demonstrate one promising approach, zero-shot classification, for several LLMs and psychometric inventories. We conclude by highlighting open challenges and future avenues of research for AI Psychometrics.

More and more machine learning is applied to human behavior. Increasingly these algorithms suffer from a hidden—but serious—problem. It arises because they often predict one thing while hoping for another. Take a recommender system: It predicts clicks but hopes to identify preferences. Or take an algorithm that automates a radiologist: It predicts in-the-moment diagnoses while hoping to identify their reflective judgments. Psychology shows us the gaps between the objectives of such prediction tasks and the goals we hope to achieve: People can click mindlessly; experts can get tired and make systematic errors. We argue such situations are ubiquitous and call them “inversion problems”: The real goal requires understanding a mental state that is not directly measured in behavioral data but must instead be inverted from the behavior. Identifying and solving these problems require new tools that draw on both behavioral and computational science.

Psychological artificial intelligence (AI) applies insights from psychology to design computer algorithms. Its core domain is decision-making under uncertainty, that is, ill-defined situations that can change in unexpected ways rather than well-defined, stable problems, such as chess and Go. Psychological theories about heuristic processes under uncertainty can provide possible insights. I provide two illustrations. The first shows how recency—the human tendency to rely on the most recent information and ignore base rates—can be built into a simple algorithm that predicts the flu substantially better than did Google Flu Trends’s big-data algorithms. The second uses a result from memory research—the paradoxical effect that making numbers less precise increases recall—in the design of algorithms that predict recidivism. These case studies provide an existence proof that psychological AI can help design efficient and transparent algorithms.

Inequalities and injustices are thorny issues in liberal societies, manifesting in forms such as the gender–pay gap; sentencing discrepancies among Black, Hispanic, and White defendants; and unequal medical-resource distribution across ethnicities. One cause of these inequalities is implicit social bias—unconsciously formed associations between social groups and attributions such as “nurturing,” “lazy,” or “uneducated.” One strategy to counteract implicit and explicit human biases is delegating crucial decisions, such as how to allocate benefits, resources, or opportunities, to algorithms. Algorithms, however, are not necessarily impartial and objective. Although they can detect and mitigate human biases, they can also perpetuate and even amplify existing inequalities and injustices. We explore how a philosophical thought experiment, Rawls’s “veil of ignorance,” and a psychological phenomenon, deliberate ignorance, can help shield individuals, institutions, and algorithms from biases. We discuss the benefits and drawbacks of methods for shielding human and artificial decision makers from potentially biasing information. We then broaden our discussion beyond the issues of bias and fairness and turn to a research agenda aimed at improving human judgment accuracy with the assistance of algorithms that conceal information that has the potential to undermine performance. Finally, we propose interdisciplinary research questions.

One of the early goals of artificial intelligence (AI) was to create algorithms that exhibited behavior indistinguishable from human behavior (i.e., human-like behavior). Today, AI has diverged, often aiming to excel in tasks inspired by human capabilities and outperform humans, rather than replicating human cogntion and action. In this paper, I explore the overarching question of whether computational algorithms have achieved this initial goal of AI. I focus on dynamic decision-making, approaching the question from the perspective of computational cognitive science. I present a general cognitive algorithm that intends to emulate human decision-making in dynamic environments, as defined in instance-based learning theory (IBLT). I use the cognitive steps proposed in IBLT to organize and discuss current evidence that supports some of the human-likeness of the decision-making mechanisms. I also highlight the significant gaps in research that are required to improve current models and to create higher fidelity in computational algorithms to represent human decision processes. I conclude with concrete steps toward advancing the construction of algorithms that exhibit human-like behavior with the ultimate goal of supporting human dynamic decision-making.

Much discussion about large language models and language-and-vision models has focused on whether these models are intelligent agents. We present an alternative perspective. First, we argue that these artificial intelligence (AI) models are cultural technologies that enhance cultural transmission and are efficient and powerful imitation engines. Second, we explore what AI models can tell us about imitation and innovation by testing whether they can be used to discover new tools and novel causal structures and contrasting their responses with those of human children. Our work serves as a first step in determining which particular representations and competences, as well as which kinds of knowledge or skill, can be derived from particular learning techniques and data. In particular, we explore which kinds of cognitive capacities can be enabled by statistical analysis of large-scale linguistic data. Critically, our findings suggest that machines may need more than large-scale language and image data to allow the kinds of innovation that a small child can produce.