TL;DR: Cross-cultural analysis of social norms using shame- and pride-related conversations in movie subtitles from Bollywood and Hollywood.
Abstract: Understanding how social norms vary across cultures can help us build culturally aligned NLP systems. In this paper, we explore self-conscious emotions, $\textit{shame}$ and $\textit{pride}$, to identify behavioral phenomena, which, in turn, highlight corresponding social norms. This paper proposes a culture-agnostic approach for norm discovery to analyze cross-cultural variations in social norms. We present the first multicultural self-conscious emotions dataset, obtained from ~5.4K Bollywood and Hollywood movies, along with over 10k extracted social norms. We validate our dataset using native speakers and demonstrate how our dataset reveals variations in social norms that align with the cultural dichotomy observed in these nations -- e.g., Bollywood movies emphasize shame due to deviation from social roles, and express pride in family honor, while Hollywood shames poverty and incompetence, and takes pride in ethical behavior. Notably, vulnerable groups across both cultures face more social sanctions than benefits based on these norms.
Paper Type: long
Research Area: Computational Social Science and Cultural Analytics
Contribution Types: NLP engineering experiment, Data resources, Data analysis
Languages Studied: English
0 Replies
Loading