Conversational Pattern Mining using Motif Detection

TL;DR

This paper introduces an unsupervised method for mining conversational patterns using motif detection, adapted from bioinformatics, applied to real-world dialogue data to identify recurring conversational motifs.

Contribution

It extends bioinformatics motif detection algorithms to NLP for conversational pattern mining without requiring labeled data.

Findings

Successfully extracted motifs from film script dialogues

Demonstrated the applicability of the method on real-world data

Provided insights into recurring conversational structures

Abstract

The subject of conversational mining has become of great interest recently due to the explosion of social and other online media. Supplementing this explosion of text is the advancement in pre-trained language models which have helped us to leverage these sources of information. An interesting domain to analyse is conversations in terms of complexity and value. Complexity arises due to the fact that a conversation can be asynchronous and can involve multiple parties. It is also computationally intensive to process. We use unsupervised methods in our work in order to develop a conversational pattern mining technique which does not require time consuming, knowledge demanding and resource intensive labelling exercises. The task of identifying repeating patterns in sequences is well researched in the Bioinformatics field. In our work, we adapt this to the field of Natural Language Processing and make several extensions to a motif detection algorithm. In order to demonstrate the application of the algorithm on a dynamic, real world data set; we extract motifs from an open-source film script data source. We run an exploratory investigation into the types of motifs we are able to mine.