International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

Research on Online Review Based on LDA Subject Model


Affiliations
1 School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China
 

The text topic analysis is the core element of the comprehensive review of clothing products, which can directly understand the views and consumption trends of consumer groups, taking a brand clothing store in JD.com as the research object, by using Python crawler and HANLP natural language processing technology, seven of the top-selling fashion reviews were classified and analyzed. Word frequency statistics, TF-IDF and other methods were used to quantify the text, this paper uses the visualization techniques such as word cloud graph contrast, pyLDAvis dynamic model and Sankey graph to display customers’ attention points and real shopping needs from various angles. The experimental results show that the visual results of online review research based on the theme model of Lda can clearly show the advantages and disadvantages of customer-centered evaluation and clothing, and provide important reference for merchants to improve decision-making and optimize service.

Keywords

Clothing Review; Natural Language Processing; Topic Mining; Visualization.
User
Notifications
Font Size

  • . Chen Huan, Huang Bo, Zhu Yimin, etc. . Short text sentiment classification method combining LDA and Self-Attention [ j ] . Computer engineering and applications, 2020,56(18) : 165-1709(in Chinese)

  • . Liang Jiye, Qiao Jie, Cao Fuyuan, etc. . Distributed representation model for short text analysis. Computer Research and development, 2018,55(8) : 1631-1640(in Chinese)

  • . Wu Fan, Wang Zhongqing, Zhou Xiabing, et Al. . Joint Model for sentiment analysis and review quality detection based on user and product representations [ j ] . Journal of Software Engineering, 2020,31(8) : 2492-2507

  • . Amjad Osmani, Jamshid Bagherzadeh Mohasefi, Farhad Soleimanian Gharehchopogh. Enriched Latent Dirichlet Allocation for Sentiment Analysis. 2020, 37(4):n/a-n/a.

  • . Guxian Da, Narissa, Gao Huan, etc. . Gaussian LDA based topic mining for online reviews [ j ] . Journal of Information Science, 2020,39(6) : 630-639(in Chinese)

  • . Li Lin, Liu Jinxing, Meng Xiangfu, etc. . Product recommendation model based on fusion scoring Matrix and review text. Journal of Computer Science, 2018,41(7) : 1559-1573(in Chinese)

  • . Feng Xingjie and Zeng Yunze. In-depth recommendation model based on scoring Matrix and review text. Journal of Computer Science, 2020,43(5) : 884-900(in Chinese)

  • . Huang Jiajia, Li Peng Wei, Peng Min, etc. . Research on topic model based on deep learning. Journal of Computer Science, 2020,43(5) : 827-855. (in Chinese)

  • . Zhang Fei, Zhang Libo, Luo Tiejian, etc. . Feature-based collaborative clustering model [ j ] . Computer Research and development, 2018,55(7) : 1508-1524(in Chinese)

  • . Chen Jiaying, Yu Jiong, Yang Xingyao. A recommendation Algorithm for feature extraction based on semantic analysis. Computer Research and development, 2020,57(3) : 562-575(in Chinese)

  • . Wang Jianxin, Prince Ya, Tian Xuan. A survey of text detection and recognition in natural scenes based on deep learning. Journal of Software Engineering, 2020,31(5) : 1465-1496(in Chinese)

  • . Zhao Chuanjun, Wang Suge, Li Deyu. Progress in cross-domain text sentiment classification [ j ] . Journal of Software Engineering, 2020,31(6) : 1723-1746(in Chinese)

  • . Veena Gangadharan, Deepa Gupta. Recognizing Named Entities in Agriculture Documents using LDA based Topic Modelling Techniques. 2020, 171:1337-1345.

  • . Tiao-juan Han, Jian-feng Lu, Li Tao. Evaluation Research and Application of Cloud Service Provider Based on Real-Time Data. //DESTECH press, USA. 20202nd International Conference ON Advanced Control, AUTOMATION AND ARTIFICIAL INTELLIGENCE (ACAAI 2020,2ND INTERNATIONAL CONFERENCE ON ADVANCED CONTROL, AUTOMATION AND ARTIFICIAL INTELLIGENCE) proceedings. 2020:156-162.

  • . Jiang Feng, Chu Xiaomin, Xu Sheng, et al. . Macro-text primary-secondary relation recognition method based on topic similarity [ C ] . //Chinese Information Society. Proceedings of the 16th National Conference on Computational Linguistics and the 5th International Symposium on Natural Language Processing based on natural labeled big data. 2017:1-10. (in Chinese)

  • . Zhou Bei. Research on Data Mining Algorithm Based on Micro-blog of Multi-view Clustering Model. Francis. 20185th INTERNATIONAL CONFERENCE ON ELECTRICAL & Electronics Engineering and Computer Science (ICEEECS 2018) proceedings. 2018:220-226.

  • . Sanjan S Malagi, Rachana Radhakrishnan, Monisha R, Keerthana S, Dr D V Ashoka. Content Modelling Intelligence System Based On Automatic Text Summarization. Int. J. Advanced Networking and Applications, 2020,11(6):4458-4467

  • . Samah Osama M, Kamel, SanaaAbouElhamayed. Multi-Tenant Endorsement using Linguistic Model for Cloud Computing. Int. J. Advanced Networking and Applications,2020.11 (6): 4486-4493 (2020)


Abstract Views: 230

PDF Views: 0




  • Research on Online Review Based on LDA Subject Model

Abstract Views: 230  |  PDF Views: 0

Authors

Guo Tao
School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China
Wu Shi-qi
School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China
Shi Yi-Cheng
School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China
Ma Qian-Qian
School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China
Tang Zhi-hang
School of Computer and Communication, Hunan Institute of Engineering Xiangtan 411104, China

Abstract


The text topic analysis is the core element of the comprehensive review of clothing products, which can directly understand the views and consumption trends of consumer groups, taking a brand clothing store in JD.com as the research object, by using Python crawler and HANLP natural language processing technology, seven of the top-selling fashion reviews were classified and analyzed. Word frequency statistics, TF-IDF and other methods were used to quantify the text, this paper uses the visualization techniques such as word cloud graph contrast, pyLDAvis dynamic model and Sankey graph to display customers’ attention points and real shopping needs from various angles. The experimental results show that the visual results of online review research based on the theme model of Lda can clearly show the advantages and disadvantages of customer-centered evaluation and clothing, and provide important reference for merchants to improve decision-making and optimize service.

Keywords


Clothing Review; Natural Language Processing; Topic Mining; Visualization.

References