Shashanka Subrahmanya

All Publications

• A computational model of reward learning and habits on social media. Nature communications Turner, G., Gunschera, L. J., Subrahmanya, S., Salecha, A., Eichstaedt, J. C., Palminteri, S., Orben, A. 2026

  Abstract

  Social media have fundamentally transformed how we live and communicate. However, the methods to study how our cognitive systems interact with technology platforms are very limited. Computational modelling represents a new avenue to uncover the finegrained cognitive processes driving social media behaviour. Here, we develop a computational model of real-world social media posting data, adapted from the animal reward learning literature. Using a Twitter (currently X) dataset (n = 2696 users), including a preregistered replication, we show that a hybrid reinforcement learning and habitual cognitive process underlies social media posting behaviour. More frequent posters show more signs of habitual behaviour. Further, younger people and women are more driven by reinforcement learning - updating their strategy more adaptively to maximise social media rewards - while older users and men are more habitual.

  View details for DOI 10.1038/s41467-026-73547-6

  View details for PubMedID 42243108

• No Good Time to Negotiate? Effective Track Two Dialogue in Protracted Israel-Palestine Conflict Escalation CONFLICT RESOLUTION QUARTERLY Fink, O., Graf, W., Subrahmanya, S., Salecha, A., Eichstaedt, J. C. 2026

  View details for DOI 10.1002/crq.70032

  View details for Web of Science ID 001700862100001

• Large language models display human-like social desirability biases in Big Five personality surveys. PNAS nexus Salecha, A., Ireland, M. E., Subrahmanya, S., Sedoc, J., Ungar, L. H., Eichstaedt, J. C. 2024; 3 (12): pgae533

  Abstract

  Large language models (LLMs) are becoming more widely used to simulate human participants and so understanding their biases is important. We developed an experimental framework using Big Five personality surveys and uncovered a previously undetected social desirability bias in a wide range of LLMs. By systematically varying the number of questions LLMs were exposed to, we demonstrate their ability to infer when they are being evaluated. When personality evaluation is inferred, LLMs skew their scores towards the desirable ends of trait dimensions (i.e. increased extraversion, decreased neuroticism, etc.). This bias exists in all tested models, including GPT-4/3.5, Claude 3, Llama 3, and PaLM-2. Bias levels appear to increase in more recent models, with GPT-4's survey responses changing by 1.20 (human) SD and Llama 3's by 0.98 SD, which are very large effects. This bias remains after question order randomization and paraphrasing. Reverse coding the questions decreases bias levels but does not eliminate them, suggesting that this effect cannot be attributed to acquiescence bias. Our findings reveal an emergent social desirability bias and suggest constraints on profiling LLMs with psychometric tests and on this use of LLMs as proxies for human participants.

  View details for DOI 10.1093/pnasnexus/pgae533

  View details for PubMedID 39691446

• Robust language-based mental health assessments in time and space through social media. NPJ digital medicine Mangalik, S., Eichstaedt, J. C., Giorgi, S., Mun, J., Ahmed, F., Gill, G., V Ganesan, A., Subrahmanya, S., Soni, N., Clouston, S. A., Schwartz, H. A. 2024; 7 (1): 109

  Abstract

  In the most comprehensive population surveys, mental health is only broadly captured through questionnaires asking about "mentally unhealthy days" or feelings of "sadness." Further, population mental health estimates are predominantly consolidated to yearly estimates at the state level, which is considerably coarser than the best estimates of physical health. Through the large-scale analysis of social media, robust estimation of population mental health is feasible at finer resolutions. In this study, we created a pipeline that used ~1 billion Tweets from 2 million geo-located users to estimate mental health levels and changes for depression and anxiety, the two leading mental health conditions. Language-based mental health assessments (LBMHAs) had substantially higher levels of reliability across space and time than available survey measures. This work presents reliable assessments of depression and anxiety down to the county-weeks level. Where surveys were available, we found moderate to strong associations between the LBMHAs and survey scores for multiple levels of granularity, from the national level down to weekly county measurements (fixed effects β = 0.34 to 1.82; p < 0.001). LBMHAs demonstrated temporal validity, showing clear absolute increases after a list of major societal events (+23% absolute change for depression assessments). LBMHAs showed improved external validity, evidenced by stronger correlations with measures of health and socioeconomic status than population surveys. This study shows that the careful aggregation of social media data yields spatiotemporal estimates of population mental health that exceed the granularity achievable by existing population surveys, and does so with generally greater reliability and validity.

  View details for DOI 10.1038/s41746-024-01100-0

  View details for PubMedID 38698174

  View details for PubMedCentralID PMC11065872

• The Language of Conflict Transformation: Assessing Psychological Change Patterns in Israeli-Palestinian Track Two Interactive Problem Solving NEGOTIATION AND CONFLICT MANAGEMENT RESEARCH Fink, O., Graf, W., Subrahmanya, S., Salecha, A., Eichstaedt, J. C. 2024; 17 (2): 130-152

  View details for DOI 10.34891/svxv-s665

  View details for Web of Science ID 001247374700002