Dataset and Baseline for Automatic Student Feedback Analysis

Abstract

In this paper, we present a student feedback corpus that contains 3000 instances of feedback written by university students. This dataset has been annotated for aspect terms, opinion terms, polarities of the opinion terms towards targeted aspects, and document-level opinion polarities. We developed a hierarchical taxonomy for aspect categorisation, which covers many aspects of the teaching-learning process. We annotated both implicit and explicit aspects using this taxonomy. Annotation methodology, difficulties faced during the annotation, and the details of the aspect term categorization are discussed in detail. Using state-of-the-art techniques, we have built baseline models for the following tasks: Target oriented Opinion Extraction, Aspect Level Sentiment Analysis, and Document Level Sentiment Analysis. These models reported 64%, 75%, and 86% F1 scores (respectively) for the considered tasks. These results illustrate the reliability and usability of the corpus for different tasks related to sentiment analysis.