Xinzhe Li, Qinglong Li, Dasom Jeong, Jaekyeong Kim
{"title":"利用特征互补性预测评论有用性的新型深度学习方法","authors":"Xinzhe Li, Qinglong Li, Dasom Jeong, Jaekyeong Kim","doi":"10.1108/jhtt-09-2023-0255","DOIUrl":null,"url":null,"abstract":"Purpose\nMost previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.\n\nDesign/methodology/approach\nFirst, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.\n\nFindings\nExtensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.\n\nOriginality/value\nTo the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.\n","PeriodicalId":51611,"journal":{"name":"Journal of Hospitality and Tourism Technology","volume":null,"pages":null},"PeriodicalIF":5.3000,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel deep learning method to use feature complementarity for review helpfulness prediction\",\"authors\":\"Xinzhe Li, Qinglong Li, Dasom Jeong, Jaekyeong Kim\",\"doi\":\"10.1108/jhtt-09-2023-0255\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Purpose\\nMost previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.\\n\\nDesign/methodology/approach\\nFirst, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.\\n\\nFindings\\nExtensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.\\n\\nOriginality/value\\nTo the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.\\n\",\"PeriodicalId\":51611,\"journal\":{\"name\":\"Journal of Hospitality and Tourism Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-05-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Hospitality and Tourism Technology\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://doi.org/10.1108/jhtt-09-2023-0255\",\"RegionNum\":3,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"HOSPITALITY, LEISURE, SPORT & TOURISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hospitality and Tourism Technology","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1108/jhtt-09-2023-0255","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"HOSPITALITY, LEISURE, SPORT & TOURISM","Score":null,"Total":0}
A novel deep learning method to use feature complementarity for review helpfulness prediction
Purpose
Most previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.
Design/methodology/approach
First, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.
Findings
Extensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.
Originality/value
To the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.
期刊介绍:
The Journal of Hospitality and Tourism Technology is the only journal dedicated solely for research in technology and e-business in tourism and hospitality. It is a bridge between academia and industry through the intellectual exchange of ideas, trends and paradigmatic changes in the fields of hospitality, IT and e-business. It covers: -E-Marketplaces, electronic distribution channels, or e-Intermediaries -Internet or e-commerce business models -Self service technologies -E-Procurement -Social dynamics of e-communication -Relationship Development and Retention -E-governance -Security of transactions -Mobile/Wireless technologies in commerce -IT control and preparation for disaster -Virtual reality applications -Word of Mouth. -Cross-Cultural differences in IT use -GPS and Location-based services -Biometric applications -Business intelligence visualization -Radio Frequency Identification applications -Service-Oriented Architecture of business systems -Technology in New Product Development