Automated Speech Act Classification For Online Chat

In this paper, we present our investigation on using supervised machine learning methods to automatically classify online chat posts into speech act categories, which are semantic categories indicating speakers’ intentions. Supervised machine learning methods presuppose the existence of annotated training data based on which machine learning algorithms can be used to learn the parameters of some model that was proposed to solve the task at hand. In our case, we used the annotated Linguistic Data Consortium chat corpus to tune our model which is based on the assumption that the first few tokens/words in each chat post are very predictive of the post’s speech act category. We present results for predicting the speech act category of chat posts that were obtained using two machine learning algorithms, Naı̈ve Bayes and Decision Trees, in conjunction with several variants of the basic model that include the first 2 to 6 words and their part-of-speech tags as features. The results support the validity of our initial assumption that the first words in an utterance can be used to predict its speech act category with very good accuracy.