We explore the use of longitudinal dialog data for two dialog prediction tasks: next message prediction and response time prediction. We show that a neural model using personal data that leverages a combination of message content, style matching, time features, and speaker attributes leads to the best results for both tasks, with error rate reductions of up to 15% compared to a classifier that relies exclusively on message content and to a classifier that does not use personal data.
The Four Dimensions of Social Network Analysis: An Overview of Research Methods, Applications, and Software Tools
David Camacho, Angel Panizo-LLedot, Gema Bello-Orgaz, Antonio Gonzalez-Pardo, Erik Cambria, Information Fusion, 2020
A Quantum-Like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis
Yazhou Zhang, Dawei Song, Xiang Li, Peng Zhang, Panpan Wang, Lu Rong, Guangliang Yu, Bo Wang, Information Fusion, 2020
Intent Classification for Dialogue Utterances
Jetze Schuurmans, Flavius Frasincar, IEEE Intelligent Systems, 2019