地理与地理信息科学

2021, v.37(04) 22-27+98

[打印本页] [关闭]
本期目录(Current Issue) | 过刊浏览(Past Issue) | 高级检索(Advanced Search)

旅游多主题情感词典的构建方法
Multi-theme Sentiment Lexicon Construction Method for Tourism

林振宇;解吉波;杨腾飞;刘战;赵静;
LIN Zhen-yu;XIE Ji-bo;YANG Teng-fei;LIU Zhan;ZHAO Jing;Hainan Provincial Key Laboratory of Earth Observation;Aerospace Information Research Institute,Chinese Academy of Sciences;East Sea Forecast Center of State Oceanic Administration;School of Surveying and Land Information Engineering,Henan Polytechnic University;University of Chinese Academy of Sciences;

摘要(Abstract):

面向旅游社交媒体大数据的分析和挖掘,该文提出一种旅游领域多主题情感词典的构建方法:首先,通过自然语言处理、机器学习,快速提取景区评价数据中旅游主题及其情感倾向,然后基于旅游多主题字典定义覆盖景区9类主题及细粒度种子主题词,最后针对景区情感倾向分析问题,根据词共现模型筛选与主题词典构成搭配的情感词,构建面向旅游领域的多主题情感词典。以海南省A级景区为例,基于上述构建的旅游领域多主题情感词典和景区网络关注度计算结果,对游客评论文本进行信息挖掘,并进一步结合GIS时空数据挖掘及网络关注度分析等方法,分析研究区域旅游景区游览信息的时空分布特征。结果表明,该文方法能有效监测景区各项主题的好评程度时空变化,验证了该方法的实用性和有效性。
Facing the analysis and mining of big data of tourism social media, this paper proposed a method of constructing multi-theme sentiment lexicon.Firstly, the natural language processing and machine learning were used to extract the tourism themes and sentiment tendency from the evaluation data of scenic spots.Then nine kinds of themes and seed keywords were defined based on the multi-theme lexicon of tourism.Finally, aiming at the sentiment tendency analysis of scenic spots, the word co-occurrence model was used to select the sentiment words matched with the theme lexicon, and then build the multi-theme sentiment lexicon.A-level scenic spots of Hainan Province were used to verify the proposed method and lexicon.Based on the multi-theme sentiment lexicon and scenic spot attention index, the tourist comments were mined from tourism social media.The spatio-temporal method of GIS and network attention analysis were used to discover the spatial and temporal characteristics of tourism information of scenic spots.And the results showed that the proposed method can effectively monitor the temporal and spatial changes of the praise degree of each theme for scenic spots in detail.

关键词(KeyWords): 旅游;多主题;情感词典;时空数据挖掘;自然语言处理
tourism;multi-theme;sentiment lexicon;spatio-temporal data mining;natural language processing

Abstract:

Keywords:

基金项目(Foundation): 海南省重大科技计划项目(ZDKJ2019006)

作者(Author): 林振宇;解吉波;杨腾飞;刘战;赵静;
LIN Zhen-yu;XIE Ji-bo;YANG Teng-fei;LIU Zhan;ZHAO Jing;Hainan Provincial Key Laboratory of Earth Observation;Aerospace Information Research Institute,Chinese Academy of Sciences;East Sea Forecast Center of State Oceanic Administration;School of Surveying and Land Information Engineering,Henan Polytechnic University;University of Chinese Academy of Sciences;

Email:

DOI:

参考文献(References):

扩展功能
本文信息
服务与反馈
本文关键词相关文章
本文作者相关文章
中国知网
分享