Skip navigation


  • DSpace logo
  • Home
  • Collections
  • Researcher Profile
  • Explore by
    • Researcher Profile
  • VGU library
  • Help
  • User Guide
  • Sign on to:
    • My DSpace
    • Receive email
      updates
    • Edit Account details

VGU RESEARCH REPOSITORY


Please use this identifier to cite or link to this item: https://epub.vgu.edu.vn/handle/dlibvgu/1259
Title: Evaluating the customer decision stages by sentiment analysis and topic modeling using data from social network - An example of US airline industry
Authors: Le Bao Toan 
Keywords: Customer decision stages;SA;Topic modeling;Data mining;Social media
Issue Date: 2021
Publisher: Vietnamese-German University
Abstract: 
Recent years witness a dramatic increase in user-generated content in social media, which gradually change customers ' shopping behaviors. The new communication channels enable online users to conveniently express and share their shopping feelings even experiences from other strangers, which then influence their purchase decision-making processes. Understanding the customer needs plays a key role in increasing customer loyalty, boost sales revenue and ensure the sustainability of companies, however, the traditional market research techniques have been usually time consuming, costly, and even inefficient. So, it is essential to have powerful assessment techniques to deeper interpret and make the most of this potential data.
The thesis aims to suggest an integrated methodology that applied sentiment analysis and top modeling algorithms to interpret the user opinions in each purchase phase of the consumer decision-making stages deeply meaningful and valuable for demanded organizations. In detail, the user-generated content collected is classified into the five phases of customer decision processes, then at each of which, sentiment analysis is used to label the users' satisfaction levels while the top modeling mechanism makes hidden topics stand out. To practice the proposed methodology, in the experiment, the study selected a dataset related to the airline industry. This is 89.148 tweets get by Twitter API, including relevant information that expressed the mentions of Twitter users when they experienced services of six different US airlines.
The generated outputs demonstrate significant effectiveness for organizations in interpreting customer opinions from overview to detail. Accordingly, they can easily offer possible solutions to make business strategies in accordance with their needs and potentials. Some major points about how businesses can improve their business operations from the results are also discussed in the study. However, the study remains some limitations in missing evaluation steps and mapping keyword rules that will be improved in the future work.
URI(1): http://epub.vgu.edu.vn/handle/dlibvgu/1259
Rights: Attribution-NonCommercial 4.0 International
Appears in Collections:Business Information Systems (BIS)

Files in This Item:
File Description SizeFormat Existing users please Login
Evaluating the customer decision stages by sentiment analysis and topic modeling using data from social network - An example of US airline industry.pdf2.19 MBAdobe PDF
Show full item record

Page view(s)

70
checked on Aug 23, 2025

Download(s)

47
checked on Aug 23, 2025

Google ScholarTM

Check


This item is licensed under a Creative Commons License Creative Commons

© Copyright 2020 by Vietnamese - German University Library.
Add: Ring road 4, Quarter 4, Thoi Hoa Ward, Ben Cat City, Binh Duong Province
Tel.:(0274) 222 0990. Ext.: 70206