Search

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. [ABSTRACT FROM AUTHOR]

This paper investigates the drivers of client satisfaction in software development and maintenance outsourcing services. Using data collected from 185 outsourcing agreements from a leading global vendor of IT services, we analyze several service quality drivers in terms of their relationship to overall satisfaction. We find that delivery of services within the originally estimated costs is the key driver that can elevate customers from being dissatisfied to satisfied. The results also suggest that the key service quality driver that moves satisfied customers toward higher levels of satisfaction is the vendor's dedicated adherence to the terms of the service level agreement. [ABSTRACT FROM AUTHOR]

Measures to extend the economic lives of products--such as remanufacturing carried out by closed-loop supply chains--are receiving increased attention because of various economic and regulatory factors. In this paper, we [...]

Cap and trade programs impose limits on industry emissions but offer individual firms the flexibility to choose among different operational levers toward compliance, including inputs, process changes, and the use [...]

Are customers in different countries alike in their preferences for similar software products? In this article, we examine the relative importance of 5 dimensions of product quality across customers from North America and Japan. Based on data collected from over 400 customers of a representative sample of electronic- (e-) commerce software products, we tested the relative importance of these quality dimensions for differences across samples from North America and Japan. We use Bayesian analysis for analyzing the average influence of each attribute on the overall customer satisfaction as well as the variability of each attribute across the two samples. Our findings indicate that the importance of quality attributes is significantly different in North American and Japanese samples. We find that although usability dominates other attributes in North American data, Japanese customers place emphasis on functionality and capability of software products. Our results provide managerial implications for the designers of global software applications, especially in the domain of e-commerce. [ABSTRACT FROM AUTHOR]