Assisting Composition of Email Responses: a Topic Prediction Approach

TL;DR

This paper introduces a topic prediction method using LDA and classifiers to assist agents in composing email responses, achieving high accuracy in predicting relevant topics for next sentences in customer service emails.

Contribution

It presents a novel approach combining LDA-based topic labeling with classification to predict email reply topics, enhancing email composition assistance.

Findings

80% accuracy in top five topic predictions

Effective in a large tele- com email dataset

Potential for interactive email reply support

Abstract

We propose an approach for helping agents compose email replies to customer requests. To enable that, we use LDA to extract latent topics from a collection of email exchanges. We then use these latent topics to label our data, obtaining a so-called "silver standard" topic labelling. We exploit this labelled set to train a classifier to: (i) predict the topic distribution of the entire agent's email response, based on features of the customer's email; and (ii) predict the topic distribution of the next sentence in the agent's reply, based on the customer's email features and on features of the agent's current sentence. The experimental results on a large email collection from a contact center in the tele- com domain show that the proposed ap- proach is effective in predicting the best topic of the agent's next sentence. In 80% of the cases, the correct topic is present among the top five recommended topics (out of fifty possible ones). This shows the potential of this method to be applied in an interactive setting, where the agent is presented a small list of likely topics to choose from for the next sentence.