The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers

TL;DR

This paper introduces a novel approach to extracting human values from TikTok videos using language models, demonstrating that a two-step script-based method with few-shot learning outperforms direct extraction, and provides the first annotated dataset for this task.

Contribution

It presents the first dataset and methodology for extracting personal values from TikTok videos, showing the effectiveness of a two-step, script-based approach with few-shot language models.

Findings

Two-step approach outperforms direct extraction.

Few-shot language models outperform fine-tuned models.

First annotated dataset of TikTok videos for value analysis.

Abstract

Societal and personal values are transmitted to younger generations through interaction and exposure. Traditionally, children and adolescents learned values from parents, educators, or peers. Nowadays, social platforms serve as a significant channel through which youth (and adults) consume information, as the main medium of entertainment, and possibly the medium through which they learn different values. In this paper we extract implicit values from TikTok movies uploaded by online influencers targeting children and adolescents. We curated a dataset of hundreds of TikTok movies and annotated them according to the well established Schwartz Theory of Personal Values. We then experimented with an array of language models, investigating their utility in value identification. Specifically, we considered two pipelines: direct extraction of values from video and a 2-step approach in which videos are first converted to elaborated scripts and values are extracted from the textual scripts. We find that the 2-step approach performs significantly better than the direct approach and that using a few-shot application of a Large Language Model in both stages outperformed the use of a fine-tuned Masked Language Model in the second stage. We further discuss the impact of continuous pretraining and fine-tuning and compare the performance of the different models on identification of values endorsed or confronted in the TikTok. Finally, we share the first values-annotated dataset of TikTok videos. To the best of our knowledge, this is the first attempt to extract values from TikTok specifically, and visual social media in general. Our results pave the way to future research on value transmission in video-based social platforms.