Web 2.0 Environmental Scanning and Adaptive Decision Support for Business Mergers and Acquisitions

Abstract

Figure A1 depicts an overview of the coevolution process controlled by the proposed HCGA algorithm. The Level II (high-level) population consists of individuals representing the feasible values of the application parameters. The Level I (low-level) populations represent two sets of system parameters (i.e., two species). One of the low-level populations represents the system parameters that drive the sentiment analysis process, whereas the second low-level population represents the system parameters that control the business relation mining process. The HCGA algorithm controls the evolutionary processes among all of the populations. At the end of the coevolution process, a set of near-optimal application parameter values and low-level NLP features (e.g., the use of specific sentiment lexicons) with respect to a particular M&A situation are obtained to refine the M&A target scoring function (i.e., the decision support mechanism).

Predicting hotel review helpfulness: The impact of review visibility, and interaction between hotel stars and review ratings

“…The academic literature already has support for Stanford POS tagger's accuracy (e.g., Chua & Banerjee, 2016;Lau, Liao, Wong, & Chiu, 2012;Yan et al, 2015), but we would like to ensure that the same tagger still maintains its high level of accuracy using our data. An experiment is designed to answer this question before we conduct formal analyses in the later sections.…”

“…OpinionFinder was used in the present study to perform subjectivity analysis to automatically identify opinions and sentiments from texts (Baccianella, Esuli, & Sebastiani, 2010;Lau, Liao, Wong, & Chiu, 2012;Wiebe & Riloff, 2005). Each word is marked with its part-of-speech (POS) tag and polarity.…”

In free float: Developing Business Analytics support for carsharing providers

“…The breadth of Business Analytics applications is illustrated by the variety of recent publications. Topics include the relationship between advertisements and purchasing decisions [36], resource allocation in emergency response scenarios [37], energy security in a changing world climate [38], as well as decision support for mergers and acquisitions [39].…”

New Media and Strategy Research: Towards a Relational Agency Approach

“…This generated widespread interest in 'big data' analyses. Business intelligence is also being enhanced by digital data, which improves strategy making in relation to, for instance, mergers and acquisitions (Lau et al 2012) or strategic goal setting (García-Moya et al 2013). Digital data have become the basis for new ways of understanding and dealing with the market.…”

“…The implications for strategy are mostly expressed in terms of 'differentiation', 'control', 'value appropriation' and 'strategic choices and decisions'. García-Moya et al 2013;Grover and Kohli 2013;Lau et al 2012). This is evident in analyses of the consequences of digital data production for strategy.…”