Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Milkova, Maria, Rudnev, Maksim, Okolskaya, Lidia
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.08968
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917134532083712
author Milkova, Maria
Rudnev, Maksim
Okolskaya, Lidia
author_facet Milkova, Maria
Rudnev, Maksim
Okolskaya, Lidia
contents Basic values are concepts or beliefs which pertain to desirable end-states and transcend specific situations. Studying personal values in social media can illuminate how and why societal values evolve especially when the stimuli-based methods, such as surveys, are inefficient, for instance, in hard-to-reach populations. On the other hand, user-generated content is driven by the massive use of stereotyped, culturally defined speech constructions rather than authentic expressions of personal values. We aimed to find a model that can accurately detect value-expressive posts in Russian social media VKontakte. A training dataset of 5,035 posts was annotated by three experts, 304 crowd-workers and ChatGPT. Crowd-workers and experts showed only moderate agreement in categorizing posts. ChatGPT was more consistent but struggled with spam detection. We applied an ensemble of human- and AI-assisted annotation involving active learning approach, subsequently trained several classification models using embeddings from various pre-trained transformer-based language models. The best performance was achieved with embeddings from a fine-tuned rubert-tiny2 model, yielding high value detection quality (F1 = 0.77, F1-macro = 0.83). This model provides a crucial step to a study of values within and between Russian social media users.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08968
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Detecting value-expressive text posts in Russian social media
Milkova, Maria
Rudnev, Maksim
Okolskaya, Lidia
Computation and Language
Artificial Intelligence
Basic values are concepts or beliefs which pertain to desirable end-states and transcend specific situations. Studying personal values in social media can illuminate how and why societal values evolve especially when the stimuli-based methods, such as surveys, are inefficient, for instance, in hard-to-reach populations. On the other hand, user-generated content is driven by the massive use of stereotyped, culturally defined speech constructions rather than authentic expressions of personal values. We aimed to find a model that can accurately detect value-expressive posts in Russian social media VKontakte. A training dataset of 5,035 posts was annotated by three experts, 304 crowd-workers and ChatGPT. Crowd-workers and experts showed only moderate agreement in categorizing posts. ChatGPT was more consistent but struggled with spam detection. We applied an ensemble of human- and AI-assisted annotation involving active learning approach, subsequently trained several classification models using embeddings from various pre-trained transformer-based language models. The best performance was achieved with embeddings from a fine-tuned rubert-tiny2 model, yielding high value detection quality (F1 = 0.77, F1-macro = 0.83). This model provides a crucial step to a study of values within and between Russian social media users.
title Detecting value-expressive text posts in Russian social media
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2312.08968