Understand customer reviews with less data and in short time: pretrained language representation and active learning

TL;DR

This paper presents a method combining pretrained language models and active learning to efficiently perform customer review analysis with limited data and reduced training time.

Contribution

It introduces an integrated approach that leverages pretrained language representations and active learning to enable fast, automatic review categorization and sentiment analysis with minimal labeled data.

Findings

Enhanced model performance using pretrained language models.

Accelerated training process through active learning.

Achieved fully automatic review analysis with limited data.

Abstract

In this paper, we address customer review understanding problems by using supervised machine learning approaches, in order to achieve a fully automatic review aspects categorisation and sentiment analysis. In general, such supervised learning algorithms require domain-specific expert knowledge for generating high quality labeled training data, and the cost of labeling can be very high. To achieve an in-production customer review machine learning enabled analysis tool with only a limited amount of data and within a reasonable training data collection time, we propose to use pre-trained language representation to boost model performance and active learning framework for accelerating the iterative training process. The results show that with integration of both components, the fully automatic review analysis can be achieved at a much faster pace.