Online Review Consistency Matters: An Elaboration Likelihood Model Perspective

2021 | Information Systems Frontiers | Citations: 20

Authors: Aghakhani, Navid; Oh, Onook; Gregg, Dawn G.; Karimi, Jahangir

Abstract: To date, online review usefulness studies have explored the independent influenc ... Expand

Abstract: To date, online review usefulness studies have explored the independent influence of central and peripheral cues on online review usefulness. Employing the Elaboration Likelihood Model (ELM), however, we argue that central and peripheral cues are jointly, not independently, processed by online users. For this exploration, we develop and measure “review consistency” variable (i.e., level of consistency between a review text and its attendant review rating), and rating inconsistency (i.e., level of inconsistency between a review rating and the average rating). We find a positive effect of review consistency on the review usefulness. Contrary to our hypothesis, however, we find a positive effect of rating inconsistency on the review usefulness. Our results also indicate that the contingency effect of rating inconsistency on the relationship between review consistency and review usefulness. Particularly, we find that rating inconsistency negatively moderates the effect of review consistency on the review usefulness. The theoretical and practical implications of the findings are discussed. Collapse

Topics: online review user-generated content memory-based reasoning electronic commerce

Methods: support vector machine random forest classification statistical hypothesis test term frequency–inverse document frequency machine learning

Theories: elaboration likelihood model

Corporate Social Responsibility Reports: Understanding Topics via Text Mining

2015 | Americas Conference on Information Systems | Citations: 0

Authors: Castellanos, Arturo; Parra, Carlos; Tremblay, Monica

Abstract: This study utilizes Text Data Mining (TDM) to analyze the contents of Corporate ... Expand

Abstract: This study utilizes Text Data Mining (TDM) to analyze the contents of Corporate Social Responsibility (CSR) Reports. The goal is to find evidence that environmental sustainability has become embedded in corporate policy and the core business discourse of seven organizations over 2004-2012. Results from supervised modeling techniques suggest embeddedness of environmental qualities in the business discourse. Unsupervised techniques provide additional support for embeddedness—as business topics tend to increasingly group with environmental ones. The process we outline should facilitate pattern discovery in documents, minimizing or eliminating the need for time-consuming content analysis that is frequently used in qualitative research. To our knowledge, this is one of the first attempts to apply TDM processing to analyze unstructured data from CSR reports. Collapse

Topics: social capital environmental sustainability human resource management accounting standard memory-based reasoning

Methods: machine learning computational algorithm supervised learning qualitative content analysis unsupervised learning

Analyzing Corporate Social Responsibility Reports Using Unsupervised and Supervised Text Data Mining

2015 | DESRIST | Citations: 0

Authors: Tremblay, Monica Chiarini; Parra, Carlos; Castellanos, Arturo

Abstract: The literature shows that companies have matured on how they see and understand ... Expand

Abstract: The literature shows that companies have matured on how they see and understand CSR—even to the extent of seeing it as an essential element of the firm’s strategy. As part of a comprehensive research agenda, we investigate CSR reports from seven Dow Jones companies to assess the embeddedness of Environmental Sustainability considerations into their Core Business discourse. We leverage the use of supervised and unsupervised Text Data Mining (TDM) techniques to analyze data from these seven companies. To our knowledge, this is one of the first attempts to apply TDM processing to analyze unstructured data from CSR reports. The process we outline should facilitate pattern discovery in documents, minimizing or eliminating the need for time-consuming content analysis that is frequently used in qualitative research. Collapse

Topics: environmental sustainability social capital memory-based reasoning human resource management corporate social responsibility

Methods: machine learning artificial neural network classification method cluster analysis qualitative content analysis

Knowledge Discovery Through Experiential Learning From Business and Other Contemporary Data Sources: A Review and Reappraisal

2011 | Information Systems Management | Citations: 4

Authors: Zurada, Jozef; Karwowski, Waldemar

Abstract: Every day massive amount of data is generated, collected, and stored in informat ... Expand

Abstract: Every day massive amount of data is generated, collected, and stored in information repositories such as databases and data warehouses. Current information technology is sufficiently mature and powerful to store any amount of raw data in an organized manner. However, finding useful patterns, trends, rules, correlations, and deviations in large amount of data, and/or making meaningful predictions from it still remains one of the main challenges of the information era. The more data one has, the more difficult it is to analyze and draw meaningful conclusions. Knowledge discovery in databases (KDD) and data mining (DM) is a field, which uses computer-based and analytic technologies to efficiently extract intelligence from data that humans need. In this article, we review the process of knowledge discovery in databases, and describe selected methodologies, methods and tools, tasks, basic learning paradigms, and applications for knowledge generation by computer learning from data instances. We also examine the current trends in the field with respect to the data types mined, data mining methods used, classes of data mining applications, as well as the data mining software used. Collapse

Topics: memory-based reasoning fraud detection database system online learning system structured query language

Methods: machine learning computational algorithm cluster analysis decision tree classification k-nearest neighbor