Hello & Goodbye: Conversation Boundary Identification Using Text Classification
Abstract
One of the main challenges in discourse analysis is the process of segmenting text into meaningful topic segments. While this problem has been studied over the past thirty years, previous topic segmentation studies ignore... [ view full abstract ]
One of the main challenges in discourse analysis is the process of segmenting text into meaningful topic segments. While this problem has been studied over the past thirty years, previous topic segmentation studies ignore crucial elements of a conversation: an opening and closing remark. Our motivation to revisit this problem space is the rise of instant message usage. We consider the problem of topic segmentation as a machine learning classification one. Using both enterprise and open source datasets, we address the question as to whether a machine learning algorithm can be trained to identify salutations and valedictions within multi-party real-time chat conversations. Our results show that both Na\"ive Bayes and Support Vector Machine (SVM) algorithms provide a reasonable degree of precision(mean F1 score: 0.58).
Authors
-
Jonathan Dunne
(Maynooth University)
-
David Malone
(Maynooth University)
Topic Areas
Modelling and System Identification , AI and Machine Learning , Data analytics
Session
Fr1b » Modelling & Identification (10:00 - Friday, 22nd June, 02.016 (Ashby))
Presentation Files
The presenter has not uploaded any presentation files.