Why some products compete and others don't: A competitive attribution model from customer perspective

2023 | Decision Support Systems | Citations: 0

Authors: Qian, Yang; Jiang, Yuanchun; Shang, Jennifer; Chai, Yidong; Liu, Yezheng

Abstract: Competitive intelligence uses information collected about competitors to derive ... Expand

Abstract: Competitive intelligence uses information collected about competitors to derive better managerial insights. In this study, we focus on identifying the competitors and detecting the competitive dimensions concurrently. To achieve this goal, we propose an aspect-level competitive attribution model (a variation of the topic model) to leverage consumer-reviewed products and their review texts. To better analyze product relations and the un­ derlying competitive aspects, we consider consumer limited attention when modeling consumers' preferences and introduce a background aspect to filter out the trivial and maintain the valuable competition-related in­ formation in review texts. We validate this approach using a dataset of 785 products reviewed by 15,669 con­ sumers in the auto industry. Based on the empirical experiments, we show that our model can accurately infer high-quality competitive segments and decipher competition-related aspects corresponding to these segments. To highlight differences, we conduct comparisons and find our approach outperforms the benchmark models meaningfully in the literature when predicting consumers' online behaviors. Collapse

Topics: online review competitive intelligence marketing management competitive advantage user-generated content

Methods: topic model experiment Gibbs sampling natural language processing computational algorithm

Software Components and Product Variety in a Platform Ecosystem: A Dynamic Network Analysis of WordPress

2023 | Information Systems Research | Citations: 0

Authors: Um, Sungyong; Zhang, Bin; Wattal, Sunil; Yoo, Youngjin

Abstract: Software components, such as application programming interfaces (APIs), provided ... Expand

Abstract: Software components, such as application programming interfaces (APIs), provided by both the platform owner and external developers in a platform ecosystem are vital to online digital platforms. These APIs are associated with functionality provided by the platform. A larger number of APIs used is generally associated with an increase in the platform ecosystem’s variety of products. However, the precise nature of the relationship between the use of APIs and product variety in a platform ecosystem is not yet known because of the lack of appropriate methodologies to analyze the complex data generated in such platform ecosystems. Drawing on a recombinatorial design perspective, we use a dynamic network model to create metrics for product variety in a digital ecosystem and study how the use of different types of APIs affects product variety. In particular, we theorize that, contrary to existing models, the structure of APIs in a large platform ecosystem is not limited to a core–periphery structure, but includes an additional third layer that we refer to as the regular core. We further hypothesize that external APIs in the regular core play a crucial role in increasing product variety in the ecosystem. To test our hypothesis, we conduct an empirical study using longitudinal data of all available digital product (i.e., plug-in) source codes on WordPress.org, the world’s largest content management system and one of the most extensive digital platform ecosystems. By analyzing all of the plug-ins on WordPress over 10 years from its inception, we find the support of our three-layer structure of APIs in a platform ecosystem: complete core, regular core, and periphery. Our empirical analysis further supports the role of external APIs in the regular core in increasing product variety. We, however, find that the strength of this effect diminishes in a newly created product category. History: Param Singh, Senior Editor; Pallab Sanyal, Associate Editor. Funding: This work was supported by the Ministry of Education Singapore [Grants R-253-000-122-133 and T1-251RES1916], the National Science Foundation [Grants 1261977 and 1120966], and Club Informatique des Grandes Entreprises Françaises. Supplemental Material: The e-companion is available at https://doi.org/10.1287/isre.2022.1172. Collapse

Topics: application programming interface digital ecosystem digital product innovation management website

Methods: doc2vec hierarchical clustering longitudinal research cluster analysis chi squared test

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

From free to fee: Monetizing digital content through expected utility-based recommender systems

2022 | Information & Management | Citations: 0

Authors: Lee, Dongwon; Nam, Kihwan; Han, Ingoo; Cho, Kanghyun

Abstract: This study proposes a novel framework for designing business rule analytics to a ... Expand

Abstract: This study proposes a novel framework for designing business rule analytics to assist businesses offering digital content in effectively converting free-only users (FOUs) into paying customers. Based on the theory of expected utility, we expand upon traditional frequency-driven rule analytics by integrating three business-relevant factors (target size, conversion profit, and conversion likelihood) into the process of generating recommendations for FOUs in digital content markets. The framework was tested using two different types of empirical analysis. We conducted a field experiment collaborating with a nationwide e-book store to determine how FOUs responded to the recommendations generated under the proposed framework. Furthermore, we analyzed over 5 million transactions collected from the e-book seller and a mobile application provider to examine the impact of customer segmentation on the effectiveness of our approach. Our findings suggest that business analytics derived from the utility-based mechanisms can significantly enhance digital content providers’ business performance. Collapse

Topics: ebook digital good mobile application recommender system analytical information system

Methods: experiment archival research field experiment descriptive statistic Bayesian analysis

Tweet to the Top? Social Media Personal Branding and Career Outcomes

2021 | Management Information Systems Quarterly | Citations: 2

Authors: Chen, Yanzhen; Rui, Huaxia; WHINSTON, ANDREW

Abstract: This paper studies whether social media personal branding (PB) improves a job c ... Expand

Abstract: This paper studies whether social media personal branding (PB) improves a job candidate's labor market performance in the context of executive employment and compensation. We focus on executives employed by Standard & Poor's 500 constituent companies from 2010 to 2013 and evaluate their PB on social media by analyzing their Twitter accounts. To disentangle the effect of PB from that of personality traits, we exploit a (positive) shock to the effectiveness of PB caused by a series of technology upgrades by Twitter. Estimations from a two-sided matching model suggest that social media PB benefits executive candidates in job markets. This paper contributes to the literature by initiating the study of the emerging phenomenon of social media PB and testing its effect on job market performance. Collapse

Topics: Twitter social media social capital advertising management IT career

Methods: autocorrelation analysis descriptive statistic robustness check longitudinal research propensity score matching

A Hybrid Approach of Machine Learning and Lexicons to Sentiment Analysis: Enhanced Insights from Twitter Data of Natural Disasters

2021 | Information Systems Frontiers | Citations: 7

Authors: Mendon, Shalak; Dutta, Pankaj; Behl, Abhishek; Lessmann, Stefan

Abstract: The success factor of sentimental analysis lies in identifying the most occurrin ... Expand

Abstract: The success factor of sentimental analysis lies in identifying the most occurring and relevant opinions among users relating to the particular topic. In this paper, we develop a framework to analyze users’ sentiments on Twitter on natural disasters using the data pre-processing techniques and a hybrid of machine learning, statistical modeling, and lexicon-based approach. We choose TF-IDF and K-means for sentiment classification among affinitive and hierarchical clustering. Latent Dirichlet Allocation, a pipeline of Doc2Vec and K-means used to capture themes, then perform multi-level polarity indices classification and its time series analysis. In our study, we draw insights from 243,746 tweets for Kerala’s 2018 natural disasters in India. The key findings of the study are the classification of sentiments based on similarity and polarity indices and identifying themes among the topics discussed on Twitter. We observe different sets of emotions and influencers, among others. Through this case example of Kerala floods, it shows how the government and other organizations could track the positive/negative sentiments concerning time and location; gain a better understanding of the topic of discussion trending among the public, and collaborate with crucial Twitter users/influencers to spread and figure out the gaps in the implementation of schemes in terms of design and execution. This research’s uniqueness is the streamlined and efficient combination of algorithms and techniques embedded in the framework used in achieving the above output, which can be integrated into a platform with GUI for further automation. Collapse

Topics: Twitter Python social media natural hazard Xing

Methods: term frequency–inverse document frequency Bayesian analysis computational algorithm doc2vec Gibbs sampling

Investigating the Effects of Dimension-Specific Sentiments on Product Sales: The Perspective of Sentiment Preferences

2021 | Journal of the Association for Information Systems | Citations: 0

Authors: Jiang, Cuiqing; Wang, Jianfei; TANG, Qian; Lyu, Xiaozhong

Abstract: While the literature has reached a consensus on the awareness effect of online ... Expand

Abstract: While the literature has reached a consensus on the awareness effect of online word-of-mouth (eWOM), this paper studies its persuasive effect-specifically, dimension-specific sentiment effects on product sales. We examine the sentiment information in eWOM along different product dimensions and reveal different persuasive effects on consumers' purchase decisions based on consumers' sentiment preference, which is defined as the relative importance that consumers place on various dimension-specific sentiments. We use an aspect-level sentiment analysis to derive dimension-specific sentiment and PVAR (panel vector auto-regression) models, and estimate their effects on product sales using a movie panel dataset. The findings show that three dimension-specific sentiments (star, genre, and plot) are positively related to movie sales. Regarding consumers' sentiment preferences, we find a positive relationship to movie sales that is stronger for plot sentiment, relative to star sentiment for low-budget movies. For high-budget movies, we find a positive relationship to movie sales that is stronger for star sentiment, relative to plot or genre sentiment. Collapse

Topics: online word of mouth word of mouth online review big data knowledge representation

Methods: sentiment analysis product review robustness check natural language processing topic model

Theories: attitude theory

Effectiveness of Location-Based Advertising and the Impact of Interface Design

2020 | Journal of Management Information Systems | Citations: 0

Authors: Molitor, Dominik; Spann, Martin; Ghose, Anindya; Reichhart, Philipp

Abstract: Offline retailers increasingly use location-based coupons to target consumers in ... Expand

Abstract: Offline retailers increasingly use location-based coupons to target consumers in their vicinity in real-time. The rationale for the use of location-based coupons is that geographic proximity increases the relevance for consumers and, thus, the effectiveness of these campaigns. Two key interface-specific aspects of location-based coupon applications that influence their effectiveness are 1) the provision of distance information and 2) the distance-based ranking of coupons. The aim of this paper is to study and quantify the impact of these two key aspects of interface design on the effectiveness of location-based coupons. We conduct a randomized field experiment with 399,913 observations, including 3,499 different coupon promotions offered by 3,930 different stores located in 2,392 ZIP code areas in a large Western European country. Our results show that the most effective interface design for location-based coupons is based on a distance-based ranking. Furthermore, we find significant differences in the impact of distance and display rank based on the interface design and the actual geographic location of users. Our results thus contribute to the understanding of consumers’ behavioral responses to location-based advertising and provide important implications for the interface-design of location-based advertising applications. Collapse

Topics: user interface usability mobile application advertising management smartphone

Methods: experimental group randomized field experiment field experiment experiment Markov chain Monte Carlo

Theories: behavioral theory

Online discrete choice models: Applications in personalized recommendations

2019 | Decision Support Systems | Citations: 3

Authors: Danaf, Mazen; Becker, Felix; Song, Xiang; Atasoy, Bilge; Ben-Akiva, Moshe

Abstract: This paper presents a framework for estimating and updating user preferences in ... Expand

Abstract: This paper presents a framework for estimating and updating user preferences in the context of app-based recommender systems. We specifically consider recommender systems which provide personalized menus of options to users. A Hierarchical Bayes procedure is applied in order to account for inter- and intra-consumer heterogeneity, representing random taste variations among individuals and among choice situations (menus) for a given individual, respectively. Three levels of preference parameters are estimated: population-level, individual-level and menu-specific. In the context of a recommender system, the estimation of these parameters is repeated periodically in an offline process in order to account for trends, such as changing market conditions. Furthermore, the individual-level parameters are updated in real-time as users make choices in order to incorporate the latest information from the users. This online update is computationally efficient which makes it feasible to embed it in a real-time recommender system. The estimated individual-level preferences are stored for each user and retrieved as inputs to a menu optimization model in order to provide recommendations. The proposed methodology is applied to both Monte-Carlo and real data. It is observed that the online update of the parameters is successful in improving the parameter estimates in real-time. This framework is relevant to various recommender systems that generate personalized recommendations ranging from transportation to e-commerce and online marketing, but is particularly useful when the attributes of the alternatives vary over time. Collapse

Topics: personalization usability recommender system willingness to pay mobile application

Methods: conjoint analysis experiment Gibbs sampling Markov chain survey

Mobile App Recommendation: An Involvement-Enhanced Approach

2019 | Management Information Systems Quarterly | Citations: 0

Authors: He, Jiangning; Fang, Xiao; Liu, Hongyan; Li, Xindan

Abstract: Given the ubiquitous and critical role of mobile apps in people's lives as well ... Expand

Abstract: Given the ubiquitous and critical role of mobile apps in people's lives as well as the sheer size of the market, developing effective mobile app recommendation methods that can help users locate the apps they desire is critical for both users and platforms. Premised in involvement theory, we propose a novel mobile app recommendation method that integrates both users' download and browsing behaviors for mobile app recommendations, in contrast to existing methods that rely on download behaviors but neglect browsing behaviors. Specifically, we introduce a novel model that appropriately combines download and browsing behaviors to learn users' overall interests in and involvement with apps, develop a new algorithm to infer the model's parameters, and propose an innovative mobile app recommendation strategy that combines users' overall interests and their current interests to recommend apps. Finally, using data collected from one of the largest mobile app platforms in China, we demonstrate and analyze the superior performance of our method over several state-of-the-art mobile app recommendation methods. Collapse

Topics: mobile application recommender system Youku digital service social network

Methods: computational algorithm digital trace data experiment Gibbs sampling field experiment

Theories: involvement theory