# User Intent Prediction in Information-seeking Conversations

## TL;DR

This paper explores methods for accurately predicting user intent in information-seeking conversations to improve conversational assistants, highlighting the importance of structural features and neural classifiers for better performance.

## Contribution

It introduces a feature importance analysis and neural classifiers that incorporate context, advancing user intent prediction in conversational search.

## Key findings

- Structural features are most influential for prediction accuracy.
- Neural classifiers with context outperform classic machine learning models.
- Insights into key factors for effective user intent prediction.

## Abstract

Conversational assistants are being progressively adopted by the general population. However, they are not capable of handling complicated information-seeking tasks that involve multiple turns of information exchange. Due to the limited communication bandwidth in conversational search, it is important for conversational assistants to accurately detect and predict user intent in information-seeking conversations. In this paper, we investigate two aspects of user intent prediction in an information-seeking setting. First, we extract features based on the content, structural, and sentiment characteristics of a given utterance, and use classic machine learning methods to perform user intent prediction. We then conduct an in-depth feature importance analysis to identify key features in this prediction task. We find that structural features contribute most to the prediction performance. Given this finding, we construct neural classifiers to incorporate context information and achieve better performance without feature engineering. Our findings can provide insights into the important factors and effective methods of user intent prediction in information-seeking conversations.