The Multimedia Sentiment Model Based on Online Homestay Reviews

Full Text (PDF, 311KB), PP.13-23

Views: 0 Downloads: 0


Wenguang Song 1,2 Hanyu Li 1,* Qian Yu 2 Wan Li 1 Bingxin Zhang 1 Qiujuan Zhang 1 Zhigang Liu 3

1. School of Computer Science, Yangtze University, Jingzhou, Hubei 430100, China

2. School of Computer Science, University of Regina, Regina, Saskatchewan S4S 0A2, Canada

3. Control Technology Institute, Wuxi Institute of Technology, Wuxi, Jiangsu 214121, China

* Corresponding author.


Received: 17 Jul. 2020 / Revised: 21 Jul. 2020 / Accepted: 26 Jul. 2020 / Published: 8 Aug. 2020

Index Terms

homestay, online review, image-text fusion, user score, CNN.


Aiming at the fact that traditional sentiment analysis is based on text, without considering the factors such as special symbols and emoticon images, which can’t fully extract the user's emotions, this paper proposes a sentiment analysis method of online homestay reviews based on image-text fusion. For text datasets, first use Word2vec to build a topic clustering model, then find the corresponding topic attribute dictionary through the topic center words, use Bayesian classifier is used for sentiment analysis, compared with SVM and decision tree methods, to evaluate the effect; For the picture dataset, Convolutional Neural Network (CNN) model is initialized by parameter migration, and image sentiment classification model is obtained by fine-tuning training of CNN model after parameter migration; Finally, the fusion method is designed to calculate the emotional probability of image-text, then judge the emotional polarity and compare it with the user's score,  The accuracy rate is 88.6%, which is higher than that of text sentiment analysis model or image sentiment analysis model. The experimental results show that the sentiment analysis of image-text fusion has better classification effect on image-text reviews and more effectively avoid the problem of inconsistency between user ratings and the emotion expressed in comments.

Cite This Paper

Wenguang Song, Hanyu Li, Qian Yu, Wan Li, Bingxin Zhang, Qiujuan Zhang, Zhigang Liu, " The Multimedia Sentiment Model Based on Online Homestay Reviews ", International Journal of Engineering and Manufacturing (IJEM), Vol.10, No.4, pp.13-23, 2020. DOI: 10.5815/ijem.2020.04.02


[1]Zhang Sijia, and Qian Yipei. "Research on the Development Obstacles and Countermeasure of Hostel in the Background of Shared Economy. " Market Modernization ,2018(18):194-195.

[2]Campos, Víctor, Brendan Jou, and Xavier Giró-I-Nieto. "From Pixels to Sentiment: Fine-Tuning Cnns for Visual Sentiment Prediction *." Image & Vision Computing (2017): S0262885617300355.

[3]Bo, Pang, and Lillian Lee. "Opinion Mining and Sentiment Analysis." Opinion Mining & Sentiment Analysis.

[4]Shi Wei, Wang Hongwei, and He Shaoyi. "Sentiment Analysis of Chinese Online Reviews Based on Semantics. Opinion Mining & Sentiment Analysis." Journal of the China Society for Scientific and Technical Information, 2013, 32(8): 860-867. 

[5]Arnold, Thomas M. "When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks." Journal of Finance 66, no. 1 (2011): 35-65.

[6]Deng Pei, Tan Changgeng. "Multimedia sentiment analysis on micro-blog based on transition variable." Application Research of Computers,2018,35(07):124-127.

[7]You, Quanzeng, Jiebo Luo, Hailin Jin, and Jianchao Yang. "Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks."  (2015).

[8]Tan J, Xu M, Lin S, Jia X, editors. "Sentiment Analysis for Images on Microblogging by Integrating Textual Information with Multiple Kernel Learning." Pacific Rim International Conference on Trends in Artificial Intelligence; 2016.

[9]Cai Guoyong, and Xia Binbin. "Multimedia Sentiment Analysis Based on Convolutional Neural Network." Journal of Computer Applications. 2016;36(2):428-431.

[10]Miao Yuqing, Wang Junhong, Liu Tonglai,et al. "Joint Vissual-textual Approach for Microblog Sentiment Analysis".Computer Engineering and Design,2019,40(04):1099-1105.

[11]Jiao Feng. "Analysis of the emotional tendency of hotel review based on naive bayes." Modern Computer,2018(20):45-49.

[12]Zhang Decheng, Wang Yang, Zhao Chuanxin, Zhen Lei, and Li Chang. "Minimal text classification model based on bayesian decision." Journal of Chongqing University of Science and Technology,2018,20(04):82-85.

[13]Tian Zhu. "Research on sentiment analysis based on deep feature extraction". Shandong University,2017.

[14]Rehurek R,Sojka P."Software framework for topic modelling with large corpora//Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks.", 2010.

[15]Kanayama, Hiroshi, and TETSUYA NASUKAWA. "Unsupervised Lexicon Induction for Clause-Level Detection of Evaluations." Natural Language Engineering 18, no. 1 (2012): 83-107.

[16]Vadivel A , Sural S, Majumdar A K . "Color-texture feature extraction using soft decision from the HSV color space// International Symposium on Intelligent Multimedia." IEEE, 2004.

[17]Wu Weifang, Gao Baojun, Yang Haixia,et al. "Impact of review text on hotel satisfaction: method based on sentiment analysis." Data Analysis and Knowledge Discovery,2017,1(03):62-71.