Value expression of different text variations

Pak, Irina * (2020) Value expression of different text variations. Masters thesis, Sunway University.

Full text not available from this repository.

Abstract

Online comments and reviews are often used by the customer to evaluate the quality of products and services purchased. Analyzing those reviews can be useful in many ways like understanding consumer opinion, improving services and decision-making processes. However, most of the time, those reviews do not consist of low case text only. People on social media and online forums use textual variations to add or emphasize feelings and emotions to their text. These textual variations include letter capitalization and repetition, exclamation marks, emoticons and so on. Sentiment analysis is defined as determining the emotional level of the text. There are many sentiment tools available today. However, not all can detect different variations of the text and measure its sentiment value. Thus, this study proposes a framework for measuring Value Expressions (VE). VE is a measure of human expressions within the written text with consideration of different textual variations. Weighting measurement was applied to identify the scoring value for each of the text variations. Evaluation of the proposed framework was executed by building a prototype based on the proposed framework. Furthermore, a dataset of online reviews was tested on the proposed prototype. Consistency of scoring for VE framework showed improvement of 8.46% in comparison with the base sentiment tool without consideration of text variations. The outcome of this study plays an important role in bringing sentiment analysis to another level where various textual variations are taking into account.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Sunway University > School of Engineering and Technology [formerly School of Science and Technology until 2020] > Dept. Computing and Information Systems
Depositing User: Ms Yong Yee Chan
Date Deposited: 29 Sep 2023 01:24
Last Modified: 29 Sep 2023 01:38
URI: http://eprints.sunway.edu.my/id/eprint/2405

Actions (login required)

View Item View Item