@inproceedings{mangalik-etal-2025-capturing,
title = "Capturing Author Self Beliefs in Social Media Language",
author = "Mangalik, Siddharth and
V. Ganesan, Adithya and
Wheeler, Abigail and
Kerry, Nicholas and
Clifton, Jeremy D. W. and
Schwartz, H. Andrew and
Boyd, Ryan L.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.69/",
doi = "10.18653/v1/2025.acl-long.69",
pages = "1362--1376",
ISBN = "979-8-89176-251-0",
abstract = "Measuring the prevalence and dimensions of self beliefs is essential for understanding human self-perception and various psychological outcomes. In this paper, we develop a novel task for classifying language that contains explicit or implicit mentions of the author{'}s self beliefs. We contribute a set of 2,000 human-annotated self beliefs, 100,000 LLM-labeled examples, and 10,000 surveyed self belief paragraphs. We then evaluate several encoder-based classifiers and training routines for this task. Our trained model, SelfAwareNet, achieved an AUC of 0.944, outperforming 0.839 from OpenAI{'}s state-of-the-art GPT-4o model. Using this model we derive data-driven categories of self beliefs and demonstrate their ability to predict valence, depression, anxiety, and stress. We release the resulting self belief classification model and annotated datasets for use in future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mangalik-etal-2025-capturing">
<titleInfo>
<title>Capturing Author Self Beliefs in Social Media Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Mangalik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adithya</namePart>
<namePart type="family">V. Ganesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abigail</namePart>
<namePart type="family">Wheeler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Kerry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="given">D</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="given">Andrew</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Boyd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Measuring the prevalence and dimensions of self beliefs is essential for understanding human self-perception and various psychological outcomes. In this paper, we develop a novel task for classifying language that contains explicit or implicit mentions of the author’s self beliefs. We contribute a set of 2,000 human-annotated self beliefs, 100,000 LLM-labeled examples, and 10,000 surveyed self belief paragraphs. We then evaluate several encoder-based classifiers and training routines for this task. Our trained model, SelfAwareNet, achieved an AUC of 0.944, outperforming 0.839 from OpenAI’s state-of-the-art GPT-4o model. Using this model we derive data-driven categories of self beliefs and demonstrate their ability to predict valence, depression, anxiety, and stress. We release the resulting self belief classification model and annotated datasets for use in future research.</abstract>
<identifier type="citekey">mangalik-etal-2025-capturing</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.69</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.69/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1362</start>
<end>1376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Capturing Author Self Beliefs in Social Media Language
%A Mangalik, Siddharth
%A V. Ganesan, Adithya
%A Wheeler, Abigail
%A Kerry, Nicholas
%A Clifton, Jeremy D. W.
%A Schwartz, H. Andrew
%A Boyd, Ryan L.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F mangalik-etal-2025-capturing
%X Measuring the prevalence and dimensions of self beliefs is essential for understanding human self-perception and various psychological outcomes. In this paper, we develop a novel task for classifying language that contains explicit or implicit mentions of the author’s self beliefs. We contribute a set of 2,000 human-annotated self beliefs, 100,000 LLM-labeled examples, and 10,000 surveyed self belief paragraphs. We then evaluate several encoder-based classifiers and training routines for this task. Our trained model, SelfAwareNet, achieved an AUC of 0.944, outperforming 0.839 from OpenAI’s state-of-the-art GPT-4o model. Using this model we derive data-driven categories of self beliefs and demonstrate their ability to predict valence, depression, anxiety, and stress. We release the resulting self belief classification model and annotated datasets for use in future research.
%R 10.18653/v1/2025.acl-long.69
%U https://aclanthology.org/2025.acl-long.69/
%U https://doi.org/10.18653/v1/2025.acl-long.69
%P 1362-1376
Markdown (Informal)
[Capturing Author Self Beliefs in Social Media Language](https://aclanthology.org/2025.acl-long.69/) (Mangalik et al., ACL 2025)
ACL
- Siddharth Mangalik, Adithya V. Ganesan, Abigail Wheeler, Nicholas Kerry, Jeremy D. W. Clifton, H. Andrew Schwartz, and Ryan L. Boyd. 2025. Capturing Author Self Beliefs in Social Media Language. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1362–1376, Vienna, Austria. Association for Computational Linguistics.