Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ahnert, Georg, Pellert, Max, Garcia, David, Strohmaier, Markus
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915550243848192
author Ahnert, Georg
Pellert, Max
Garcia, David
Strohmaier, Markus
author_facet Ahnert, Georg
Pellert, Max
Garcia, David
Strohmaier, Markus
contents This paper proposes temporally aligned Large Language Models (LLMs) as a tool for longitudinal analysis of social media data. We fine-tune Temporal Adapters for Llama 3 8B on full timelines from a panel of British Twitter users, and extract longitudinal aggregates of emotions and attitudes with established questionnaires. We focus our analysis on the beginning of the COVID-19 pandemic that had a strong impact on public opinion and collective emotions. We validate our estimates against representative British survey data and find strong positive, significant correlations for several collective emotions. The obtained estimates are robust across multiple training seeds and prompt formulations, and in line with collective emotions extracted using a traditional classification model trained on labeled data. We demonstrate the flexibility of our method on questions of public opinion for which no pre-trained classifier is available. Our work extends the analysis of affect in LLMs to a longitudinal setting through Temporal Adapters. It enables flexible, new approaches towards the longitudinal analysis of social media data.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models
Ahnert, Georg
Pellert, Max
Garcia, David
Strohmaier, Markus
Computers and Society
Computation and Language
This paper proposes temporally aligned Large Language Models (LLMs) as a tool for longitudinal analysis of social media data. We fine-tune Temporal Adapters for Llama 3 8B on full timelines from a panel of British Twitter users, and extract longitudinal aggregates of emotions and attitudes with established questionnaires. We focus our analysis on the beginning of the COVID-19 pandemic that had a strong impact on public opinion and collective emotions. We validate our estimates against representative British survey data and find strong positive, significant correlations for several collective emotions. The obtained estimates are robust across multiple training seeds and prompt formulations, and in line with collective emotions extracted using a traditional classification model trained on labeled data. We demonstrate the flexibility of our method on questions of public opinion for which no pre-trained classifier is available. Our work extends the analysis of affect in LLMs to a longitudinal setting through Temporal Adapters. It enables flexible, new approaches towards the longitudinal analysis of social media data.
title Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models
topic Computers and Society
Computation and Language
url https://arxiv.org/abs/2409.17990