A Cross-Platform Market Structure Analysis Method Using Online Product Reviews

Abstract

Studies have shown that online product reviews can indicate the position of a competitive brand. Even though reviews on different platforms may express different opinions, most studies are based on only one platform. This may lead to an inaccurate analysis of market structure. To solve this problem, we develop a novel market structure analysis based on multi-attribute group decision-making which can integrate reviews from different platforms. Multiple platforms more comprehensively reflect the market than single platforms do. To verify the effectiveness of the proposed method, we conduct a case study of mobile phone reviews across three top e-commerce platforms in China. In addition, we propose a process to generate priorities for product-attribute improvements using a cross-platform market structure analysis method. Our experiments demonstrate the effectiveness of the proposed method.

A cloud‐based and web‐based group decision support system in multilingual environment with hesitant fuzzy linguistic preference relations

“…To solve this, for instance, Wu and Liao 44 used a sentiment analysis tool “Stanford CoreNLP” to estimate a reviewer's probabilistic evaluation for a product on 1–5 scale. Kou et al 45 tested and implemented different machine learning models (e.g., support vector machine, K‐nearest neighbors) to train a sentiment classifier and then predict reviewers’ probabilistic evaluation based on input review comments. One could also deploy and host the advanced sentiment classification models such as Transformer, TextCNN, and so forth.…”

The Role of Organizational Resilience in Social, Economic, Environmental and Human Sustainability: Evidence Form Chinese FMCG Sector

“…Economic sustainability is a combined portion of sustainability and means that the business must use, protect and sustain different resources such as human resources and material resources to create long-term justifiable values by optimum use, recovery as well as recycling (Ajor & Alikor, 2020;Huang et al, 2021;Kou et al, 2021). Economic sustainability focused on the use of investment in various corporate social responsibility (CSR) activities and ensured that profit of the company must not be affected.…”

A Deep Learning-Based Sentiment Analysis Approach for Online Product Ranking With Probabilistic Linguistic Term Sets

“…In the current research [1], [9], the common way to address the problem of product ranking based on online reviews is composed of three stages: 1) product features extraction from online reviews, 2) sentiment analysis for calculating the overall sentiment scores of sentiment words of review texts, 3) ranking alternative products based on the results of the first two stages.…”

“…Furthermore, the SVM algorithm is not suitable for large data sets, especially for online review text data, since their target classes are inevitably overlapping which makes it harder for the SVM to predict the hyperplane for classification. Decision tree-based ensemble algorithms, such as random forest and gradient boosting decision tree algorithms, were also discussed and applied in a few studies [9], [25], [26] to solve the problem of sentiment classification. Onan et al [27], [28] conducted a comprehensive analysis to show that Decision tree-based ensemble algorithms could get a higher classification accuracy compared with baselearning algorithms (SVM, Naive Bayes) in text classification.…”