Relationship Identification Between Conversational Agents Using Emotion Analysis

Human relationships are influenced by the underlying emotions in their interactions. With the increasing use of social networks, relationships from textual data can also be inferred from online interactions. Such interactions result in massive amount of textual data which is available in the form of text messages, emails, and social media posts. Identification and analysis of human relationships are useful for numerous applications ranging from cybersecurity to public health. In this paper, we present a method called RIEA (Relationship Identification using Emotion Analysis), for identifying relationships between multiple intelligent agents by analyzing the conversation between them. The objective of our work is to combine concepts of cognitive psychology and natural language processing (NLP) to extract emotions and map them onto a set of relationships and analyze how relationships transform over time. We employ psychological models to label a large corpus of conversations and apply machine learning techniques to determine emotion-to-relationship mapping. We use four distinct association classes and four attachment styles using best-worst scaling method for classification. Combining the attachment and association styles given in research literature gives us the relationship combinations for our analysis. Additionally, this work studies the most common changes of behaviors and emotions and the corresponding transformations in human relationships. Our results show that RIEA can correctly detect interpersonal relationships with an accuracy of 85%. The evaluation shows that RIEA can accurately identify interpersonal relationships from conversations and can be extended for identifying more complex relationships. This study also highlights the effect of changes in emotional behavior in the development of relationships over time.

[1]  Mirza Omer Beg,et al.  A deep learning framework for clickbait detection on social area network using natural language cues , 2020, J. Comput. Soc. Sci..

[2]  Nik Bessis,et al.  Classifying emotions in Stack Overflow and JIRA using a multi-label approach , 2020, Knowl. Based Syst..

[3]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[4]  Mike Thelwall,et al.  Sentiment strength detection for the social web , 2012, J. Assoc. Inf. Sci. Technol..

[5]  Hongfei Lin,et al.  Improving User Attribute Classification with Text and Social Network Attention , 2019, Cognitive Computation.

[6]  Emily S. Cross,et al.  The Perception of Emotion in Artificial Agents , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[7]  Aqil M. Azmi,et al.  A Study of Arabic Social Media Users—Posting Behavior and Author’s Gender Prediction , 2018, Cognitive Computation.

[8]  Lin Padgham,et al.  Integrating BDI Agents with Agent-Based Simulation Platforms , 2016, Autonomous Agents and Multi-Agent Systems.

[9]  Erik Cambria,et al.  A survey on empathetic dialogue systems , 2020, Inf. Fusion.

[10]  Katie Atkinson,et al.  Modelling Mood in Co-operative Emotional Agents , 2016, DARS.

[11]  Joseph de Rivera,et al.  Emotions as social relationships , 1986 .

[12]  Jesse Fox,et al.  Romantic Partner Monitoring After Breakups: Attachment, Dependence, Distress, and Post-Dissolution Online Surveillance via Social Networking Sites , 2015, Cyberpsychology Behav. Soc. Netw..

[13]  Hsin-Chang Yang,et al.  Sentiment Discovery of Social Messages Using Self-Organizing Maps , 2018, Cognitive Computation.

[14]  Erik Cambria,et al.  Dialogue systems with audio context , 2020, Neurocomputing.