Consumers increasingly make informed buying decisions based on reading online reviews for products and services. Due to the large volume of available online reviews, consumers hardly have the time and patience to read them all. This paper aims to select a compact set of high-quality reviews that can cover a specific set of product features and related consumer sentiments. Selecting such a subset of reviews can significantly save the time spent on reading reviews while preserving the information needed. A unique review selection problem is defined and modeled as a bi-objective combinatorial optimization problem, which is then transformed into a minimum-cost set cover problem that is NP-complete. Several approximation algorithms are then designed, which can sustain performance guarantees in polynomial time. Our effective selection algorithms can also be upgraded to handle dynamic situations. Comprehensive experiments conducted on six real-world datasets demonstrate that the proposed algorithms significantly outperform benchmark methods by generating a more compact review set with much lower computational cost. The number of reviews selected is much smaller compared with the quantity of all available reviews, and the selection efficiency is deeply increased by accelerating strategies, making it very practical to adopt the methods in real-world online applications.
Detecting nodal activities in dynamic social networks has strategic importance in many applications, such as online marketing campaigns and homeland security surveillance. How peerto-peer exchanges in social media can facilitate nodal activity detection is not well explored. Existing models assumes network nodes to be static in time and do not adequately consider features from social theories. This research developed and validated two theory-based models, Random Interaction Model (RIM) and Preferential Interaction Model (PIM), to characterize temporal nodal activities in social media networks of human agents. The models capture the network characteristics of randomness and preferential interaction due to community size, human bias, declining connection cost, and rising reachability. The models were compared against three benchmark models (abbreviated as EAM, TAM, and DBMM) using a social-media community consisting of 790,462 users who posted over 3,286,473 tweets and formed more than 3,055,797 links during 2013-2015. The experimental results show that both RIM and PIM outperformed EAM and TAM significantly in accuracy across different dates and time windows. Both PIM and RIM scored significantly smaller errors than DBMM did. Structural properties of social networks were found to provide a simple and yet accurate approach to predicting model performances. These results indicate the models' strong capability of accounting for user interactions in real-world social media networks and temporal activity detection. The research should provide new approaches for temporal network activity detection, develop relevant new measures, and report new findings from large social media datasets.
Online communities that curate knowledge are critically dependent on high-quality contributions from anonymous expert users. Understanding users? motivation to contribute knowledge helps practitioners design such websites for optimal user contribution and user benefits. Researchers have studied reciprocity as a motivation for users to share knowledge online. In this study, we focus on two different types of reciprocity as drivers of online contribution: ex post and ex ante reciprocity. Ex post reciprocity is when users who receive help from others in the past, pay back by helping others. Controlling for extrinsic motivation and behavioral pattern, we test whether users who receive more answers last week will answer more questions in the current week on StackOverflow.com. We find a significant positive relationship between ex post reciprocity and knowledge contribution, and such a reciprocal motivation diminishes with time. Ex ante reciprocity is when people help others in expectation of future help from others. Using data from StackOverflow.com, we take advantage of a natural experiment with a difference-in-differences (DID) analysis and find evidence supporting the existence of ex ante reciprocity. This study offers a new taxonomy for reciprocity and new insights on how reciprocity drives online knowledge sharing.
Effective use of online consumer reviews is hampered by uncertainty about their helpfulness. Despite emerging efforts in identifying antecedents of review helpfulness, they have largely overlooked rich semantic relationships embedded in online reviews. To address the literature gap, this study probes review text by uncovering semantic relationships among product features. We introduce three novel factors - breadth, depth, and redundancy, to gain a deep understanding of review helpfulness. Drawing on product uncertainty and information quality theories, we conceptualize and operationalize the proposed factors based on a semantic hierarchy of product features. The evaluation results on both experience and search goods lend strong support to those factors in improving both theoretical understanding and practical assessment of review helpfulness. Breadth and depth also offer new lens for explaining mixed findings about some other factors in the literature.
Recommender Systems are nowadays successfully used by all major web sites---from e-commerce to social media---to filter content and to make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is scattered. In this research commentary, we review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quantification of the business effects of recommenders and the performance assessment of recommendation algorithms in academia.
Under what conditions is the Internet more likely to be used maliciously for criminal activity? This study examines the conditions under which the Internet is associated with cybercriminal offenses. Using comprehensive state-level data in the United States during 2004-2010, our findings show that there is no clear empirical evidence that the Internet penetration rate is related to the number of Internet crime perpetrators; however, cybercriminal activities are contingent upon socioeconomic factors and connection speed. Specifically, a higher income, more education, a lower poverty rate, a lower unemployment rate, and a lower inequality are likely to make the Internet penetration be more positively related with cybercrime perpetrators, which are indeed different from the conditions of terrestrial crime in the real world. In addition, broadband connections are significantly and positively associated with Internet crime perpetrators, though narrowband connections are not. Taken together, cybercrime requires more than just a skilled perpetrator, and it requires an infrastructure to facilitate profiteering from the act. A relevant discussion is provided.