Explainable Artificial Intelligence-Based Competitive Factor Identification
- 20 July 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 16 (1), 1-11
- https://doi.org/10.1145/3451529
Abstract
Competitor analysis is an essential component of corporate strategy, providing both offensive and defensive strategic contexts to identify opportunities and threats. The rapid development of social media has recently led to several methodologies and frameworks facilitating competitor analysis through online reviews. Existing studies only focused on detecting comparative sentences in review comments or utilized low-performance models. However, this study proposes a novel approach to identifying the competitive factors using a recent explainable artificial intelligence approach at the comprehensive product feature level. We establish a model to classify the review comments for each corresponding product and evaluate the relevance of each keyword in such comments during the classification process. We then extract and prioritize the keywords and determine their competitiveness based on relevance. Our experiment results show that the proposed method can effectively extract the competitive factors both qualitatively and quantitatively.Keywords
Funding Information
- National Research Foundation of Korea
- Korea government (2020R1F1A1067914)
This publication has 29 references indexed in Scilit:
- Aspect extraction for opinion mining with a deep convolutional neural networkKnowledge-Based Systems, 2016
- Affective Computing and Sentiment AnalysisIEEE Intelligent Systems, 2016
- Identifying comparative customer requirements from product online reviews for competitor analysisEngineering Applications of Artificial Intelligence, 2016
- Multi-document text summarization for competitor intelligencePublished by Association for Computing Machinery (ACM) ,2015
- A Rule-Based Approach to Aspect Extraction from Product ReviewsPublished by Association for Computational Linguistics (ACL) ,2014
- DLIREC: Aspect Term Extraction and Term Polarity Classification SystemPublished by Association for Computational Linguistics (ACL) ,2014
- Fine-grained Product Features Extraction and Categorization in Reviews Opinion MiningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Mine Your Own Business: Market-Structure Surveillance Through Text MiningMarketing Science, 2012
- Deriving the Pricing Power of Product Features by Mining Consumer ReviewsManagement Science, 2011
- Cumulated gain-based evaluation of IR techniquesACM Transactions on Information Systems, 2002