The future of large language models in social science research: Reply to Berger (2024) and Carrillo et al. (2024).

In their commentaries, Berger (2024) and Carrillo et al. (2024) raise several thoughtful questions regarding machine-assisted hypothesis generation in the social sciences. We discuss their ideas and build upon them.

Machine-assisted social psychology hypothesis generation.

Social psychology research projects begin with generating a testable idea that relies heavily on a researcher's ability to assimilate, recall, and accurately process available research findings. However, an exponential increase in new research findings is making the task of synthesizing ideas across the multitude of topics challenging, which could result in important overlooked research connections. In this research, we leverage the fact that social psychology research is based on verbal models and employ large natural language models to generate hypotheses that can aid social psychology researchers in developing new research hypotheses.

Does the first letter of one's name affect life decisions? A natural language processing examination of nominative determinism.

This research examines whether the phenomenon of nominative determinism (a name-driven outcome) exists in the real world. Nominative determinism manifests as a preference for a profession or city to live in that begins with the same letter as a person's own name. The literature presents opposing views on this phenomenon, with one stream of research documenting the influence and another stream questioning the existence and generalizability of the effect, as well as the proposed underlying process.

Religion and reactance to COVID-19 mitigation guidelines.

During the current COVID-19 pandemic, religious gatherings have become intense hot spots for the spread of the virus. In this research, we focus on the religiosity of communities to examine whether religiosity helps or hinders adherence to mitigation policies such as shelter-in-place directives. Prior research has made opposing predictions as to the influence of religiosity.

The Perils of Leading a Democracy.

Environmental characteristics can influence aging. Democracy results in higher life expectancy for its members. However, there is a lack of research that indicates the influence of democracy on its leaders.

How language shapes prejudice against women: An examination across 45 world languages.

Language provides an ever-present context for our cognitions and has the ability to shape them. Languages across the world can be gendered (language in which the form of noun, verb, or pronoun is presented as female or male) versus genderless. In an ongoing debate, one stream of research suggests that gendered languages are more likely to display gender prejudice than genderless languages.

Thinking Outside the Euclidean Box: Riemannian Geometry and Inter-Temporal Decision-Making.

Inter-temporal decisions involves assigning values to various payoffs occurring at different temporal distances. Past research has used different approaches to study these decisions made by humans and animals. For instance, considering that people discount future payoffs at a constant rate (e.

In praise of vagueness: malleability of vague information as a performance booster.

Is the eternal quest for precise information always worthwhile? Our research suggests that, at times, vagueness has its merits. Previous research has demonstrated that people prefer precise information over vague information because it gives them a sense of security and makes their environments more predictable. However, we show that the fuzzy boundaries afforded by vague information can actually help individuals perform better than can precise information.

Border bias: the belief that state borders can protect against disasters.

In this research, we documented a bias in which people underestimate the potential risk of a disaster to a target location when the disaster spreads from a different state, but not when it spreads from an equally distant location within the same state. We term this the border bias. Following research on categorization, we propose that people consider locations within a state to be part of the same superordinate category, but consider locations in two different states to be parts of different superordinate categories.

The group-contagion effect: the influence of spatial groupings on perceived contagion and preferences.

We used contagion theory as a framework for studying the influence of spread of qualities in a group. We found that people's preferences change depending on how objects are arranged in a group. They prefer to choose from a closely arranged group if one unidentified object in that group has a positive quality, but prefer to choose from a group in which objects are farther apart if one unidentified object in that group has a negative quality.