Angamuthu Swathi, Trojovský Pavel
Department of Mathematics, University of Hradec Králové, Rokitanskeho, Hradec Kralove, Czech Republic.
PeerJ Comput Sci. 2023 Aug 17;9:e1497. doi: 10.7717/peerj-cs.1497. eCollection 2023.
Expert assessments with pre-defined numerical or language terms can limit the scope of decision-making models. We propose that decision-making models can incorporate expert judgments expressed in natural language through sentiment analysis. To help make more informed choices, we present the Sentiment Analysis in Recommender Systems with Multi-person, Multi-criteria Decision Making (SAR-MCMD) method. This method compiles the opinions of several experts by analyzing their written reviews and, if applicable, their star ratings. The growth of online applications and the sheer amount of available information have made it difficult for users to decide which information or products to select from the Internet. Intelligent decision-support technologies, known as recommender systems, leverage users' preferences to suggest what they might find interesting. Recommender systems are one of the many approaches to dealing with information overload issues. These systems have traditionally relied on single-grading algorithms to predict and communicate users' opinions for observed items. To boost their predictive and recommendation abilities, multi-criteria recommender systems assign numerous ratings to various qualities of products. We created, manually annotated, and released the technique in a case study of restaurant selection using 'TripAdvisor reviews', 'TMDB 5000 movies', and an 'Amazon dataset'. In various areas, cutting-edge deep learning approaches have led to breakthrough progress. Recently, researchers have begun to focus on applying these methods to recommendation systems, and different deep learning-based recommendation models have been suggested. Due to its proficiency with sparse data in large data systems and its ability to construct complex models that characterize user performance for the recommended procedure, deep learning is a formidable tool. In this article, we introduce a model for a multi-criteria recommender system that combines the best of both deep learning and multi-criteria decision-making. According to our findings, the suggested system may give customers very accurate suggestions with a sentiment analysis accuracy of 98%. Additionally, the metrics, accuracy, precision, recall, and F1 score are where the system truly shines, much above what has been achieved in the past.
使用预定义的数值或语言术语进行专家评估可能会限制决策模型的范围。我们建议决策模型可以通过情感分析纳入以自然语言表达的专家判断。为了帮助做出更明智的选择，我们提出了具有多人多标准决策的推荐系统中的情感分析（SAR-MCMD）方法。该方法通过分析多位专家的书面评论以及（如适用）他们的星级评分来汇总他们的意见。在线应用的增长和可用信息的海量使得用户难以决定从互联网上选择哪些信息或产品。智能决策支持技术，即推荐系统，利用用户的偏好来推荐他们可能感兴趣的内容。推荐系统是处理信息过载问题的众多方法之一。这些系统传统上依赖单级算法来预测和传达用户对观察到的项目的意见。为了提高其预测和推荐能力，多标准推荐系统会为产品的各种品质赋予多个评分。我们在使用“ TripAdvisor评论”、“ TMDB 5000电影”和“亚马逊数据集”进行餐厅选择的案例研究中创建、手动注释并发布了该技术。在各个领域，前沿的深度学习方法都取得了突破性进展。最近，研究人员开始关注将这些方法应用于推荐系统，并提出了不同的基于深度学习的推荐模型。由于深度学习在大数据系统中处理稀疏数据的能力以及构建能够描述推荐过程中用户表现的复杂模型的能力，它是一个强大的工具。在本文中，我们介绍了一种多标准推荐系统模型，该模型结合了深度学习和多标准决策的优点。根据我们的研究结果，所建议的系统可以为客户提供非常准确的建议，情感分析准确率达到98%。此外，该系统在指标、准确率、精确率、召回率和F1分数方面表现出色，远超以往的成果。
