What is the Conversation About?: A Topic-Model-Based Approach for Analyzing Customer Sentiments in Twitter

What is the Conversation About?: A Topic-Model-Based Approach for Analyzing Customer Sentiments in Twitter

Stefan Sommer, Andreas Schieber, Kai Heinrich, Andreas Hilbert
Copyright: © 2012 |Pages: 16
DOI: 10.4018/jiit.2012010102
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In Social Commerce customers evolve to be an important information source for companies. Customers use the communication platforms of Web 2.0, for example Twitter, in order to express their sentiments about products or discuss their experiences with them. These sentiments can be very important for the development of products or the enhancement of marketing strategies. The research goal is to analyze customer sentiments in Twitter. The first step in the research is the detection of topics in Twitter entries which contain patterns of interest. For the topic detection, the authors use Latent Dirichlet Allocation for topic modeling. The authors found event based topics in the exemplary context of Sony’s 3D TV sets. In future work, the authors will implement sentiment analysis algorithms in order to determine sentiments in the entries corresponding to the detected topics.
Article Preview
Top

2. Methodology

The goal of our research work in this paper is the development of an algorithm which is able to identify microblog entries containing sentiments in a particular context. In order to reach our goal we make use of the design science approach by Hevner et al. (2004). The purpose of Hevner’s approach is gaining new insights by the development of an artifact which solves a specific problem. In our case the specific problem is the identification of Twitter entries containing sentiments or testimonials about Sony TV products in the context of 3D technology. The artifact is used to evaluate the possible methods for our system.

During our research we answer the following research questions:

  • 1.

    What capabilities and challenges occur while analyzing microblog entries as a result of the limited amount of characters?

  • 2.

    What kind of methods exists in order to automatically identify topics in microblog entries and how can we detect them?

Complete Article List

Search this Journal:
Reset
Volume 20: 1 Issue (2024)
Volume 19: 1 Issue (2023)
Volume 18: 4 Issues (2022): 3 Released, 1 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing