University of Twente Student Theses

Login

Gender Perceptions in chatbots : The Role of Linguistic features

Prakash, Meenakshi (2024) Gender Perceptions in chatbots : The Role of Linguistic features.

[img] PDF
1MB
Abstract:Many conversational agents are assigned female gender, which, coupled with their roles as assistants and the language they use, can reinforce gender stereotypes. Exploring and designing agents and those that challenge these stereotypes is cru cial for ethical design that focuses on gender equality. This study investigates the factors that contribute to the perception of gender in conversational agents, focusing specifically on linguistic features. While designers often gender chatbots through names, pronouns, and avatars, research has shown that less explicit linguistic cues within the conversation can also influence gender perception. Despite extensive research on gender-based linguistic differences, the impact of specific linguistic fea tures on chatbot gender perception has not been thoroughly examined. This study addresses this gap by examining how linguistic features like intensifiers and emo tional language, which have been observed at higher rates in female speech and writing, influence gender perception. Using a between-subjects design, the experi ment involves three chatbots: one incorporating intensifiers, one incorporating emo tional language, and a control chatbot without these features. The results show a slight trend in the expected direction, suggesting that linguistic features might influ ence participants’ gender perception of the chatbot. However, these findings are not statistically significant. The trend points to the potential value of further study to ex plore whether linguistic features affect gender perception. Given the subtle nuances of language, more research is necessary to gain a deeper understanding.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:17 linguistics and theory of literature, 50 technical science in general, 54 computer science
Programme:Interaction Technology MSc (60030)
Link to this item:https://purl.utwente.nl/essays/103822
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page