Document Type

Dissertation

Rights

This item is available under a Creative Commons License for non-commercial use only

Disciplines

1.2 COMPUTER AND INFORMATION SCIENCE

Publication Details

Dissertation submitted in partial fulfillment of the requirements of Dublin Institute of Technology for the degree of M.Sc. in Computing (Advanced Software Computing) 2017.

Abstract

In the field of sentiment classification, much research has been done on reviews of topics such as movies, software and books. Little research has been done in the airline service domain. In the airline industry, the use of social media as a customer service tool has become a growing phenomenon. The research conducted by Wan and Gao (2015) has proposed an ensemble classification approach for airline service sentiment classification using Twitter data. In accordance, the objective of improving the performance of ensemble classification approach is the primary consideration. This research proposed new hybrid classification approach that uses the state-of-art approach proposed by Wan and Gao (2015) combining with lexicon based approach on classification of airline service topic using Twitter data. The research evaluated the proposed approach in depth, along with explorations of implementing expansion of tweet content in order to further improve the classification performance. In this project, the ensemble approach that consists of both machine learning approaches and lexicon based approach was analysed which suggested the improvement of the proposed classification approach performance compare with machine learning only approach on airline service domain conducted by Wan and Gao (2015).

DOI

10.21427/D7190M

Share

COinS