Sad or just jealous? Using Experience Sampling to Understand and Detect Negative Affective Experiences on Instagram

要旨

Social Network Services (SNSs) evoke diverse affective experiences. While most are positive, many authors have documented both the negative emotions that can result from browsing SNS and their impact: Facebook depression is a common term for the more severe results. However, while the importance of the emotions experienced on SNSs is clear, methods to catalog them, and systems to detect them, are less well developed. Accordingly, this paper reports on two studies using a novel contextually triggered Experience Sampling Method to log surveys immediately after using Instagram, a popular image-based SNS, thus minimizing recall biases. The first study improves our understanding of the emotions experienced while using SNSs. It suggests that common negative experiences relate to appearance comparison and envy. The second study captures smartphone sensor data during Instagram sessions to detect these two emotions, ultimately achieving peak accuracies of 95.78% (binary appearance comparison) and 93.95% (binary envy).

著者
Mintra Ruensuk
UNIST, Ulsan, Korea, Republic of
Taewan Kim
KAIST, Daejeon, Korea, Republic of
Hwajung Hong
KAIST, Deajeon, Korea, Republic of
Ian Oakley
UNIST, Ulsan, Korea, Republic of
論文URL

https://dl.acm.org/doi/abs/10.1145/3491102.3517561

動画

会議: CHI 2022

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2022.acm.org/)

セッション: Deviance Online

290
5 件の発表
2022-05-03 23:15:00
2022-05-04 00:30:00