Frontiers: In-Consumption Social Listening with Moment-to- Moment Unstructured Data: The Case of Movie Appreciation and Live Comments

摘要

Consumption of entertainment products such as movies, video games, and sports events often lasts a nontrivial time period. During these experiences, consumers are likely to encounter temporal variations in the content of consumption, to which they may react in real time. Compared with existing in-consumption analysis (e.g., eye tracking and neural activity analysis), listening to in-consumption consumers' voices on social media has great potential. Our paper proposes a new approach for in-consumption social listening and demonstrates its value in the context of online movie watching wherein viewers can react to movie content with live comments. Specifically, we propose to listen to the live comments through a novel measure, moment-to-moment synchronicity (MTMS), to capture viewers' in-consumption engagement. MTMS refers to the synchronicity between temporal variations in the volume of live comments and those in movie content mined from unstructured video, audio, and text data (i.e., camera motion, shot length, sound loudness, pitch, and spoken lines). We demonstrate that MTMS significantly predicts viewers' postconsumption appreciation of movies and that it can be evaluated at a finer level to identify engaging content. Finally, we discuss the information value of MTMS with the presence of measures used in the previous literature and the value of integrating supply-side content information into in-consumption analysis.