Emotion Analysis of Hotel Customers Reviews Based on SVM

doi:10.3969/j.issn.1006-2475.2017.03.025

Abstract

Abstract: This paper improves the accuracy of word segmentation and emotion analysis of network vocabulary and expressions by increasing the variety of emotion dictionary. On the other hand, customer reviews of a hotel are used as the original data. After extracting the amount of text features, such as positive and negative words, negative words, the degree of adverbs and the amount of special symbols, we make different feature combinations, and hope to find the optimal combination of parameters SVM including C and g through the kfold Cross Validation and grid search algorithm. Training and testing different feature combinations by SVM and analyzing the correct rate of each combination, we find out the most suitable combination of text feature and feature analysis which are used for study of user reviews of emotion. The results show that under the premise of satisfying the optimal combination of parameters C and g, the correct rate of the feature combination using positive and negative emotional words, negative words, emotion score and degree adverbs is the highest and reaches 93.4%.

Key words: emotion analysis, SVM, Kfold cross validation, grid search, feature combination

CLC Number:

TP391

SHI Qiangqiang1， ZHAO Yingding2,3， YANG Hongyun2,3. Emotion Analysis of Hotel Customers Reviews Based on SVM[J]. Computer and Modernization, 2017, 0(3): 117-.

References

［1］赵妍妍,秦兵,刘挺. 文本情感分析［J］. 软件学报, 2010,21（8）:1834-1848
［2］Balahur A, Steinberger R, Kabadjov M, et al. Sentiment analysis in the news［C］// Proceedings of the 7th International Conference on Language Resources and Evaluation （LREC2010）. 2010:2216-2220.
［3］Jiang Long, Yu Mo, Zhou Ming, et al． Targetdependent twitter sentiment classification［C］// Proc. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies．2011:151-160．
［4］杨立公，朱俭，汤世平. 文本情感分析综述［J］. 计算机应用, 2013,33（6）:1574-1578.
［5］Taboada M, Brooke J, Tofiloski M, et al．Lexiconbased methods for sentiment analysis［J］. Computational Linguistics, 2011,37（2）:267-307.
［6］Wiebe J, Bruce R F, Ohara T P. Development and use of a goldstandard data set for subjectivity classifications［C］ // Proceedings of Association for Computational Linguistics. 1999:246-253.
［7］Hatzivassiloglou V, Klavans J L, Holcombe M L, et al. SIMFINDER: A flexible clustering tool for summarization［C］// Proceedings of the Workshop on Summarization in NAACL01. 2001:41-49.
［8］Riloff E, Wiebe J. Learning extraction patterns for subjective expressions［C］// Proceeding of the 2003 Conference on Empirical Methods in Natural Language Processing. 2003:105-112.
［9］刘康,赵军. 基于层叠CRFs模型的句子褒贬度分析研究［J］. 中文信息学报, 2008,22（1）:123-128.
［10］Pang B, Lilian L, Shivakumar V. Thumbs up: Sentiment classification using machine learning techniques［C］// Proceedings of the ACL02 Conference on Empirical Methods in Natural Language Processing. 2002:79-86.
［11］李婷婷,姬东鸿. 基于SVM和CRF多特征组合的微博情感分析［J］. 计算机应用研究, 2015,32（4）:978-981.
［12］陈晓东. 基于情感词典的中文微博情感倾向分析研究［D］. 武汉:华中科技大学, 2012.
［13］Perter Harrington. Machine Learning in Action［M］ . 李锐,李鹏,曲亚东,等译. 北京:人民邮电出版社, 2013. 
［14］樊康新. 基于SVM的网络文本情感分类系统的研究与设计［J］. 计算机时代, 2015,12（9）:34-37.
［15］徐晓明. SVM参数寻优及其在分类中的应用［D］. 大连:大连海事大学, 2014.
［16］王健峰,张磊,陈国兴,等. 基于改进的网格搜索法的SVM参数优化［J］. 应用科技, 2012（3）:28-31.
［17］王兴玲, 李占斌. 基于网格搜索的支持向量机核函数参数的确定［J］. 中国海洋大学学报（自然科学版）, 2005,35（5）:859-862.

[1]	YANG Sun-zhe, SUN Ai-zhen. Rice Nitrogen Nutrition Diagnosis Based on HSV Color and LBP Texture Features [J]. Computer and Modernization, 2023, 0(07): 86-92.
[2]	ZHOU Chang-ye, LI Cheng. Prediction of Railway Freight Volume Based on GS-LSTM Model [J]. Computer and Modernization, 2022, 0(10): 24-28.
[3]	YIN Min, LI Xiao-hui, LI Chang-bao, GU Ping-li, ZHANG Ke, LYU Shou-ye. An Analysis Method of Influencing Factors of Legal Judgment Prediction [J]. Computer and Modernization, 2021, 0(04): 37-41.
[4]	HUANG Xu-bin, LIANG Shu-jie. Classification of Motor EEG Signals Based on PCA and PSO-SVM [J]. Computer and Modernization, 2021, 0(03): 70-76.
[5]	WANG Wen-wei, XIAO Jun-bi, CHENG Peng, ZHANG Yue. SDN-based DDoS Attack Defense System [J]. Computer and Modernization, 2021, 0(02): 117-121.
[6]	ZHANG Wen-hua, ZHANG Zhi-jun. SVM-based Verification Method for New Energy Bus Operation Mileage [J]. Computer and Modernization, 2020, 0(05): 39-.
[7]	XI Xing-xing, LIU Yu-hong, ZHANG Rong-fen. SVR Blood Pressure Prediction Method Based on Grid Search and Cross Validation [J]. Computer and Modernization, 2020, 0(03): 44-.
[8]	ZHANG Kai-yan1,2, PAN Yang3, LOU Ji-chao4. Fault Classification of Process Layer Network in Intelligent Substation Based on ANP-SVM [J]. Computer and Modernization, 2019, 0(07): 72-.
[9]	YANG Jin-shan, LI Zhi . Progression Prediction Model of Chronic Kidney Disease Based on #br# Sparse Logistic Regression and Multiple Ensemble Algorithm [J]. Computer and Modernization, 2019, 0(03): 13-.
[10]	ZHANG Hao1,2, ZHONG Min1,2. Chinese Short Text Classification Based on Sentence-LDA Topic Model [J]. Computer and Modernization, 2019, 0(03): 102-.
[11]	CUILi-na1,GUOHu-sheng2. ImbalancedSVMClassificationMethodBasedonIncrementalLearning [J]. Computer and Modernization, 2018, 0(07): 20-.
[12]	WANG Zheng-jie, YANG Wei-li, WANG Zhe, HOU Yu-shan, GUO Yin-jing. Research on Parameters Setting and Classification Characters of Four Classification Algorithms [J]. Computer and Modernization, 2018, 0(02): 54-.
[13]	LIU Wei, YANG Hui-jie, LIU Shou-yin. A Feature Selection Algorithm of Battery SOH Based on ACCA-FCM and SVM-RFE [J]. Computer and Modernization, 2018, 0(01): 11-18.
[14]	WEN Fang， KANG Cai-qin， CHEN Li-wen， DING Hui， XU Kun， WANG Ning-ning. Static Hand Gesture Recognition Based on RGBD Data [J]. Computer and Modernization, 2018, 0(01): 74-77.
[15]	WANG Si-yuan1, WANG Heng-sheng1,2, LIU Tong1. Recognition of Mobile Robot Natural Language Navigation Instructions Based on Word Embedding and SVM [J]. Computer and Modernization, 2017, 0(9): 24-28,55.