Extracting Actionable Insights from Text Data: A Stable Topic Model Approach

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Yang, Yi; Subramanyam, Ramanath

Abstract: Topic models are becoming a frequently employed tool in the empirical methods r ... Expand

Abstract: Topic models are becoming a frequently employed tool in the empirical methods repertoire of information systems and management scholars. Given textual corpora, such as consumer reviews and online discussion forums, researchers and business practitioners often use topic modeling to either explore data in an unsupervised fashion or generate variables of interest for subsequent econometric analysis. However, one important concern stems from the fact that topic models can be notorious for their instability, i.e., the generated results could be inconsistent and irreproducible at different times, even on the same dataset. Therefore, researchers might arrive at potentially unreliable results regarding the theoretical relationships that they are testing or developing. In this paper, we attempt to highlight this problem and suggest a potential approach to addressing it. First, we empirically define and evaluate the stability problem of topic models using four textual datasets. Next, to alleviate the problem and with the goal of extracting actionable insights from textual data, we propose a new method, Stable LDA, which incorporates topical word clusters into the topic model to steer the model inference toward consistent results. We show that the proposed Stable LDA approach can significantly improve model stability while maintaining or even improving the topic model quality. Further, employing two case studies related to an online knowledge community and online consumer reviews, we demonstrate that the variables generated from Stable LDA can lead to more consistent estimations in econometric analyses. We believe that our work can further enhance management scholars' collective toolkit to analyze ever-growing textual data. Collapse

Topics: online review user-generated content open source usability social media

Methods: topic model experiment word embedding Gibbs sampling computational algorithm

Sources and impacts of social influence from online anonymous user reviews

2018 | Information & Management | Citations: 52

Authors: Zhao, Kexin; Stylianou, Antonis C.; Zheng, Yiming

Abstract: Consumers increasingly rely on online reviews to make purchase decisions. Howeve ... Expand

Abstract: Consumers increasingly rely on online reviews to make purchase decisions. However, the process through which consumers are influenced by online reviews is not well understood. To fill the gap, we apply the social influence theory to theoretically explain and analyze this opinion change process. Specifically, we identify antecedents and consequences of two types of social influence from online user reviews: informational and value-expressive influence. From a survey conducted in a controlled laboratory environment, we found that perceived review quality positively impacts informational influence, while perceived review quality, consistency, and social presence jointly impact value-expressive influence. Interestingly, informational influence impacts both perceived decision quality and perceived usefulness of the website, while value-expressive influence only impacts perceived usefulness of the website. Surprisingly, consumer characteristics, including prior product expertise and self-monitoring, do not have significant effects on the formation of social influence online. Collapse

Topics: social influence perceived usefulness decision quality social presence website

Methods: survey PLS tool mediation analysis Amazon review conceptual modelling

Theories: social influence theory social exchange theory theory of reasoned action elaboration likelihood model social comparison theory

Data properties and the performance of sentiment classification for electronic commerce applications

2017 | Information Systems Frontiers | Citations: 7

Authors: Choi, Youngseok; Lee, Habin

Abstract: Sentiment classification has played an important role in various research area i ... Expand

Abstract: Sentiment classification has played an important role in various research area including e-commerce applications and a number of advanced Computational Intelligence techniques including machine learning and computational linguistics have been proposed in the literature for improved sentiment classification results. While such studies focus on improving performance with new techniques or extending existing algorithms based on previously used dataset, few studies provide practitioners with insight on what techniques are better for their datasets that have different properties. This paper applies four different sentiment classification techniques from machine learning (Naïve Bayes, SVM and Decision Tree) and sentiment orientation approaches to datasets obtained from various sources (IMDB, Twitter, Hotel review, and Amazon review datasets) to learn how different data properties including dataset size, length of target documents, and subjectivity of data affect the performance of those techniques. The results of computational experiments confirm the sensitivity of the techniques on data properties including training data size, the document length and subjectivity of training /test data in the improvement of performances of techniques. The theoretical and practical implications of the findings are discussed. Collapse

Topics: online review Twitter knowledge representation open source social media

Methods: experiment computational algorithm naïve bayes product review decision tree classification

Toy safety surveillance from online reviews

2016 | Decision Support Systems | Citations: 60

Authors: Winkler, Matt; Abrahams, Alan S.; Gruss, Richard; Ehsani, Johnathan P.

Abstract: Toy-related injuries account for a significant number of childhood injuries and ... Expand

Abstract: Toy-related injuries account for a significant number of childhood injuries and the prevention of these injuries remains a goal for regulatory agencies and manufacturers. Text-mining is an increasingly prevalent method for uncovering the significance of words using big data. This research sets out to determine the effectiveness of text-mining in uncovering potentially dangerous children's toys. We develop a danger word list, also known as a “smoke word” list, from injury and recall text narratives. We then use the smoke word lists to score over one million Amazon reviews, with the top scores denoting potential safety concerns. We compare the smoke word list to conventional sentiment analysis techniques, in terms of both word overlap and effectiveness. We find that smoke word lists are highly distinct from conventional sentiment dictionaries and provide a statistically significant method for identifying safety concerns in children's toy reviews. Our findings indicate that text-mining is, in fact, an effective method for the surveillance of safety concerns in children's toys and could be a gateway to effective prevention of toy product-related injuries. Collapse

Topics: online review website social media enterprise information system

Methods: experiment sentiment analysis Amazon review Student's t-test natural language processing