Human-Computer Interaction (SIG HCI)

Presenter Information

Verena Thürmel, LMU MunichFollow

Paper Type

Complete

Paper Number

1330

Description

By leveraging recent advancements in affective computing, emotion-based personalization systems provide media offerings tailored to users’ emotions. Although emotionally intelligent systems increasingly attract attention both in research and in practice, research on users’ perceptions of emotion-based personalization is sparse. Building on the personalization-privacy trade-off, I propose a comprehensive framework to investigate how the use of affective technologies for personalization impacts users’ trust mediated by their perceived benefits and threats. To test the research model, I conduct an experiment with a fictitious music personalization system and analyze the results using partial least squares structural equation modeling. The results show that emotion-based personalization positively impacts users’ trust via perceived emotional support but simultaneously hampers trust via privacy concerns and emotional creepiness.

Share

COinS
Top 25 Percent Paper badge
 
Aug 9th, 12:00 AM

I Know How You Feel: An Investigation of Users’ Trust in Emotion-Based Personalization Systems

By leveraging recent advancements in affective computing, emotion-based personalization systems provide media offerings tailored to users’ emotions. Although emotionally intelligent systems increasingly attract attention both in research and in practice, research on users’ perceptions of emotion-based personalization is sparse. Building on the personalization-privacy trade-off, I propose a comprehensive framework to investigate how the use of affective technologies for personalization impacts users’ trust mediated by their perceived benefits and threats. To test the research model, I conduct an experiment with a fictitious music personalization system and analyze the results using partial least squares structural equation modeling. The results show that emotion-based personalization positively impacts users’ trust via perceived emotional support but simultaneously hampers trust via privacy concerns and emotional creepiness.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.