基于方面情感三元组抽取的游客评论大数据细粒度情感分析

旅游科学 ›› 2024, Vol. 38 ›› Issue (8): 60-87.

基于方面情感三元组抽取的游客评论大数据细粒度情感分析

肖璐^1,2,3, 李桥兴^1,3,*, 陈怡梦², 沈加升¹, 张茜², 杨勇¹

1.贵州大学管理学院, 贵州贵阳 550025;
2.贵州商学院旅游管理学院, 贵州贵阳 550014;
3.贵州大学数字化转型与治理协同创新实验室, 贵州贵阳 550025

收稿日期:2023-10-24 修回日期:2024-07-13 出版日期:2024-08-30 发布日期:2024-09-18
通讯作者: 李桥兴^*（1973—）,男,博士后,贵州大学管理学院教授,博导,研究方向为管理科学与系统工程、产业经济学与大数据分析,E-mail：qxli@gzu.edu.cn。
作者简介:肖璐（1986—）,女,贵州大学管理学院博士生,贵州商学院旅游管理学院讲师,研究方向为管理科学与大数据分析、旅游经济与旅游消费者行为,E-mail：gs.lxiao21@gzu.edu.cn。陈怡梦（1981—）,贵州商学院旅游管理学院副教授,研究方向为旅游心理与消费者行为。沈加升（1983—）,男,贵州大学管理学院硕士生,研究方向为软件工程研发与数据分析。张茜（1988—）,女,博士,贵州商学院旅游管理学院讲师,研究方向为大数据隐私保护和旅游消费者行为。杨勇（1980—）,男,贵州大学管理学院讲师、博士生,研究方向为自然语言处理与大数据分析。
基金资助:
国家自然科学基金项目“我国南方喀斯特地区大健康产业的布局机制研究”（71663011）; 贵州大学研究基地及智库重点专项课题“新型城镇化视角下贵州智慧养老机构的布局策略研究”（GDZX2021030）

Fine-Grained Sentiment Analysis of Tourists' Reviews Big Data： Based on Aspect Sentiment Triplet Extraction

XIAO Lu^1,2,3, LI Qiaoxing^1,3,*, CHEN Yimeng², SHEN Jiasheng¹, ZHANG Qian², YANG Yong¹

1. School of Management, Guizhou University, Guiyang 550025, China;
2. School of Tourism Management, Guizhou University of Commerce, Guiyang 550014, China;
3. Collaborative Innovation Laboratory of Digital Transformation and Governance, Guizhou University, Guiyang 550025, China

Received:2023-10-24 Revised:2024-07-13 Online:2024-08-30 Published:2024-09-18

摘要/Abstract

摘要： 目前游客细粒度情感分析的研究多集中于基于主题聚类下的频次统计等的大致分析,缺乏更精准地从每一条评论中抽取所有属性情感特征的细致定量刻画。因此,文章基于国内四大知名旅游电商平台上有关贵州省数百家A级旅游景区的游客评论大数据,建构较大规模的旅游评论方面级情感分析（ABSA）中文标注数据集;采用基于BERT的LCF-AEPC方面情感三元组抽取联合模型,在近8万条主观评论文本集上端到端地实现17万余个方面情感三元组的预测输出;并基于此输出结果进行可视化量化分析,探究游客在景区不同方面以及在不同级别和不同类型景区上的情感特征差异及其原因,构建了包含四类要素的游客情感感知影响因素模型。文章通过人工智能领域的深度学习技术实现ABSA多任务可快速有效地捕捉游客对景区各方面的偏好、需求和意见等信息,将成为旅游领域细粒度情感研究的有益尝试和最新应用。

关键词: 旅游大数据, 方面级情感分析, 深度学习, 三元组抽取, 情感特征

Abstract: The current research on fine-grained sentiment analysis of tourists is mostly focused on approximate analysis based on topic clustering and frequency statistics and so on, lacking the meticulous quantitative portrayal of all aspect sentiment features extracted from each review more precisely. In this article, we constructed a large-scale ABSA Chinese annotated dataset of tourism reviews based on the big data of tourists' real reviews of hundreds of national A-level scenic spots in Guizhou Province on four well-known domestic tourism e-commerce platforms. using BERT-based LCF-AEPC aspects sentiment triplet extraction joint model, the prediction output of more than 170,000 aspect sentiment triplets were realized end-to-end on a dataset of nearly 80,000 subjective review texts. Based on the output results, a visual and quantitative analysis was conducted to explore the differences in tourists' sentiment characteristic regarding different aspects of attractions, as well as across different levels and types of attractions. Then the reasons of the differences were tried to be explained and a framework of four-element tourist sentiment impact factors was constructed. This article utilizes the deep learning techniques in the field of artificial intelligence to achieve ABSA multi-task, thereby quickly and effectively capturing the information of tourists' preferences, needs, and opinions on various aspects of tourist attractions. This will be a beneficial attempt and the latest application of fine-grained sentiment research in the field of tourism.

Key words: tourism big data, aspect sentiment analysis, deep learning, triplet extraction, sentiment features

中图分类号:

F592.7

肖璐, 李桥兴, 陈怡梦, 沈加升, 张茜, 杨勇. 基于方面情感三元组抽取的游客评论大数据细粒度情感分析[J]. 旅游科学, 2024, 38(8): 60-87.

XIAO Lu, LI Qiaoxing, CHEN Yimeng, SHEN Jiasheng, ZHANG Qian, YANG Yong. Fine-Grained Sentiment Analysis of Tourists' Reviews Big Data： Based on Aspect Sentiment Triplet Extraction[J]. TOURISM SCIENCE, 2024, 38(8): 60-87.

参考文献

[1] 蔡玉舒,曹扬,江维,等,2021.基于BERT的端到端旅游评论意见挖掘方法[J].计算机技术与发展(9):118-123.
[2] 谌志群,鞠婷,2020.基于BERT和双向LSTM的微博评论倾向性分析研究[J].情报理论与实践(8):173-177.
[3] 丛丽,何继红,2020.野生动物旅游景区游客情感特征研究——以长隆野生动物世界为例[J].旅游学刊(2):53-64.
[4] 冯庆,孙根年,2015.中国品牌旅游景区驱动因素及形成系数方程研究[J].经济管理(4):116-125.
[5] 贵州省文化和旅游厅,2023.贵州省A级旅游景区名录[EB/OL].(2023-09-05)[2023-09-23].https://www.guizhou.gov.cn/dcgz/rwgz/rmjd/202309/t20230905_82317228.html.
[6] 国显达,那日萨,崔少泽,2020.基于CNN-BiLSTM的消费者网络评论情感分析[J].系统工程理论与实践(3):653-663.
[7] 李春晓,李辉,刘艳筝,等,2020.多彩华夏:大数据视角的入境游客体验感知差异深描[J].南开管理评论(1):28-39.
[8] 梁嘉祺,姜珊,陶犁,2020.基于网络游记语义分析和GIS可视化的游客时空行为与情绪关系实证研究——以北京市为例[J].人文地理(2):152-160.
[9] 刘欣逸,宁博,王明,等,2023.基于句法增强的细粒度情感三元组抽取方法[J].计算机研究与发展(7):1649-1660.
[10] 刘逸,保继刚,陈凯琪,2017a.中国赴澳大利亚游客的情感特征研究——基于大数据的文本分析[J].旅游学刊(5):46-58.
[11] 刘逸,保继刚,朱毅玲,2017b.基于大数据的旅游目的地情感评价方法探究[J].地理研究(6): 1091-1105.
[12] 刘逸,孟令坤,保继刚,等,2021.人工计算模型与机器学习模型的情感捕捉效度比较研究——以旅游评论数据为例[J].南开管理评论(5):63-74.
[13] 马勇,李玺,2005.旅游景区管理[M].北京:中国旅游出版社.
[14] 邵党国,胡永健,2023.结合多层注意力和GCN的方面情感三元组抽取[J/OL].小型微型计算机系统:1-10.http://kns.cnki.net/kcms/detail/1106.TP.20230222.1057.012.html.
[15] 沈超,王安宁,方钊,等,2021.基于在线评论数据的产品需求趋势挖掘[J].中国管理科学(5):211-220.
[16] 史达,王乐乐,衣博文,2020.在线评论有用性的深度数据挖掘——基于TripAdvisor的酒店评论数据[J].南开管理评论(5):64-75.
[17] 王承云,戴添乐,蒋世敏,等,2022.基于网络大数据的上海红色旅游形象感知与情感评价研究[J].旅游科学(2):138-150.
[18] 王伟,王洪伟,2016.面向竞争力的特征比较网络:情感分析方法[J].管理科学学报(9):109-126.
[19] 徐琳宏,林鸿飞,杨志豪,2007.基于语义理解的文本倾向性识别机制[J].中文信息学报(1):96-100.
[20] 薛福亮,刘丽芳,2020.一种基于CRF与ATAE-LSTM的细粒度情感分析方法[J].数据分析与知识发现(Z1):207-213.
[21] 鄢慧丽,张小浩,熊浩,2023.一星即差评?评论效价对酒店评论有用性的影响:一项混合方法研究[J].旅游科学(2):77-99.
[22] 尤天慧,张瑾,樊治平,2019.基于情感分析和证据理论的多属性在线评论决策方法[J].系统管理学报(3):536-544.
[23] 郁常悦,王晓峰,2023.身未动,心追忆:个体旅游记忆的内容特征与情感反应[J/OL].旅游科学:1-15.https://doi.org/10.16323/j.cnki.lykx.20230914.001.
[24] 张旭辉,张郴,李雅南,等,2022.城市旅游餐饮体验的注意力机制模型建构——基于机器学习的网络文本深度挖掘[J].南京师大学报(自然科学版)(1):32-39.
[25] 赵春艳,陈美爱,2019.基于网络文本分析的游客满意度影响因素分析[J].统计与决策(13):115-118.
[26] 中华人民共和国中央人民政府网,2021.中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要[EB/OL].(2021-03-13)[2023-09-22]. https://www.gov.cn/xinwen/2021-03/13/content_5592681.htm.
[27] 中华人民共和国国务院,2022.国务院关于印发“十四五”旅游业发展规划的通知:国发〔2021〕32号[EB/OL].(2022-01-20)[2023-09-22].https://www.gov.cn/zhengce/content/2022-01/20/content_5669468.htm.
[28] ALI T,MARC B,OMAR B,et al.,2021.Exploring destination's negative e-reputation using aspect based sentiment analysis approach:case of Marrakech destination on TripAdvisor[J].Tourism management perspectives,40:100892.https://doi.org/10.1016/j.tmp.2021.100892.
[29] BRUN C,NIKOULINA V,2018.Aspect Based Sentiment Analysis into the Wild[C]//Proceedings of the 9th Workshop on Computational Approaches to Subjectivity,Sentiment and Social Media Analysis:116-122.
[30] CHEN J,BECKEN S,STANTIC B,2022.Assessing destination satisfaction by social media:An innovative approach using Importance-Performance Analysis[J].Annals of tourism research,93:10371.https://doi.org/10.1016/j.annals.2022.103371.
[31] CHEN Y,KONG L,WANG Y,et al.,2021.Multi-grained attention representation with ALBERT for aspect-level sentiment classification[J].IEEE access,9:106703-106713.https://doi.org/10.1109/ACCESS.2021.3100299.
[32] CHU M,CHEN Y,YANG L,et al.,2022.Language interpretation in travel guidance platform:Text mining and sentiment analysis of TripAdvisor reviews[J].Frontiers in psychology,13:1029945.https://doi.org/10.3389/fpsyg.2022.1029945.
[33] LIN T,JOE I,2023.An adaptive masked attention mechanism to act on the local text in a global context for aspect-based sentiment analysis[J].IEEE access,11:43055-43066.https://doi.org/10.1109/ACCESS.2023.3270927.
[34] LIU B,2012.Sentiment analysis and opinion mining[J].Synthesis lectures on human language technologies,5(1):1-167.
[35] LIU Y,ZHOU Y,LI Z,et al.,2023.HIM:An end-to-end hierarchical interaction model for aspect sentiment triplet extraction[J].IEEE/ACM transactions on audio,speech,and language processing,31:2272-2285.https://doi.org/10.1109/TASLP.2023.3282379.
[36] MARRESE-TAYLOR E,VELÁSQUEZ J D,BRAVO-MARQUEZ F,et al.,2013.Identifying customer preferences about tourism products using an aspect-based opinion mining approach[J].Procedia computer science,22:182-191.
[37] MEHRA P,2023.Unexpected surprise:Emotion analysis and aspect based sentiment analysis (ABSA) of user generated comments to study behavioral intentions of tourists[J].Tourism management perspectives,45:101063.https://doi.org/10.1016/j.tmp.2022.101063.
[38] MESSAOUDI C,GUESSOUM Z,BEN ROMDHANE L,2022.Opinion mining in online social media:A survey[J].Social network analysis and mining,12(1):25.
[39] PENG H,XU L,BING L,et al.,2020.Knowing What,How and Why:A Near Complete Solution for Aspect-based Sentiment Analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence,34(5):8600-8607.https://doi.org/10.1609/aaai.v34i05.6383.
[40] QIAN Y,JIANG Y,SHANG J,et al.,2023.Why some products compete and others don't:A competitive attribution model from customer perspective[J].Decision support systems,169:113956.https://doi.org/10.1016/j.dss.2023.113956.
[41] SEN S,LERMAN D,2007.Why are you telling me this?An examination into negative consumer reviews on the web[J].Journal of interactive marketing,21(4):76-94.
[42] WAN H,YANG Y,DU J,et al.,2020.Target-aspect-sentiment Joint Detection for Aspect-based Sentiment Analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence,34(5):9122-9129.https://doi.org/10.1609/aaai.v34i05.6447.
[43] WEI Z,ZHANG M,MING Y,2023.Understanding the effect of tourists' attribute-level experiences on satisfaction-a cross-cultural study leveraging deep learning[J].Current issues in tourism,26(1):105-121.
[44] WU C,XIONG Q,YI H,et al.,2021.Multiple-element joint detection for aspect-based sentiment analysis[J].Knowledge-based systems,223:107073.https://doi.org/10.1016/j.knosys.2021.107073.
[45] WU Z,YING C,ZHAO F,et al.,2020.Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction[C]//Findings of the Association for Computational Linguistics:EMNLP 2020,Online,Association for Computational Linguistics:2576-2585.https://doi.org/10.18653/v1/2020.findings-emnlp.234.
[46] XU J,WANG X,ZHANG J,et al.,2022.Explaining customer satisfaction via hotel reviews:A comparison between pre-and post-COVID-19 reviews[J].Journal of hospitality and tourism management,53:208-213.
[47] YANG H,ZENG B,YANG J H,et al.,2021.A multi-task learning model for chinese-oriented aspect polarity classification and aspect term extraction[J].Neurocomputing,419:344-356.
[48] ZENG B,YANG H,XU R,et al.,2019.LCF:A local context focus mechanism for aspect-based sentiment classification[J].Applied sciences,9(16):3389.https://doi.org/10.3390/app9163389.
[49] ZHANG C,LI Q C,SONG D W,et al.,2020.A multi-task Learning Framework for Opinion Triplet Extraction[C]//Findings of the Association for Computational Linguistics:EMNLP 2020,Online,Association for Computational Linguistics:819-828.
[50] ZHAO Y,QIN B,LIU T,2014.Creating a fine-grained corpus for chinese sentiment analysis[J].IEEE intelligent systems,30(1):36-43.
[51] ZHU L,XU M,BAO Y,et al.,2022.Deep learning for aspect-based sentiment analysis:a review[J].PeerJ computer science,8:e1044.https://doi.org/10.7717/peerj-cs.1044.