An intelligent box office predictor based on aspect-level sentiment analysis of movie review

被引:4
|
作者
Yang, Gelan [1 ]
Xu, Yiyi [2 ]
Tu, Li [3 ]
机构
[1] Hunan City Univ, Dept Comp, Yiyang, Peoples R China
[2] Guangxi Univ Sci & Technol, Sch Comp Sci & Technol, Liuzhou 545006, Peoples R China
[3] Univ Elect Sci & Technol China, Zhongshan Inst, Coll Mech Elect Engn, Zhongshan 528400, Peoples R China
关键词
Box office prediction; Sentiment analysis; Co-attention network; Word embedding; SDC; MODEL;
D O I
10.1007/s11276-023-03378-6
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Box office is a challenging and crucial task for the movie distributors in decision making. In recent years, movie reviews are widely posted and shared on intelligent multimedia systems and everywhere. In this work, we employ both the metadata of the movie and the sentiment information of the users' reviews to establish an intelligent predicting model. In the sentiment polarity classification model, a co-attention network-based aspect-level sentiment analysis strategy is developed by using the specific word embedding representations from both the contexts and the aspect. Considering the movie success prediction, a Softmax Discriminant Classifier is used due to its capable of dealing with non-linear issues. The sentiments from review texts, together with the movie information are taken as input variables of the predictor. Experimental outcomes verify the working performance of the proposed method which indicates that our model can be further applied to the sentiment analysis and the predicting of movie success.
引用
收藏
页码:3039 / 3049
页数:11
相关论文
共 50 条
  • [21] Aspect-Level Sentiment Analysis Based on Bidirectional-GRU in SIoT
    Ali, Waqar
    Yang, Yuwang
    Qiu, Xiulin
    Ke, Yaqi
    Wang, Yinyin
    IEEE ACCESS, 2021, 9 : 69938 - 69950
  • [22] An aspect-level sentiment analysis dataset for therapies on Twitter
    Guo, Yuting
    Das, Sudeshna
    Lakamana, Sahithi
    Sarker, Abeed
    DATA IN BRIEF, 2023, 50
  • [23] A Unified Probabilistic Model for Aspect-Level Sentiment Analysis
    Stantic, Daniel
    Song, Fei
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, NLPCC 2017, 2018, 10619 : 900 - 909
  • [24] Enhancing Aspect-level Sentiment Analysis with Word Dependencies
    Tian, Yuanhe
    Chen, Guimin
    Song, Yan
    16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 3726 - 3739
  • [25] Modeling Category Semantic and Sentiment Knowledge for Aspect-Level Sentiment Analysis
    Wang, Yuan
    Huo, Peng
    Tang, Lingyan
    Xiong, Ning
    Hu, Mengting
    Yu, Qi
    Yang, Jucheng
    IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2024, 15 (04) : 1962 - 1969
  • [26] Aspect-level Sentiment Analysis using AS-Capsules
    Wang, Yequan
    Sun, Aixin
    Huang, Minlie
    Zhu, Xiaoyan
    WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 2033 - 2044
  • [27] Aspect-level sentiment analysis using context and aspect memory network
    Lv, Yanxia
    Wei, Fangna
    Cao, Lihong
    Peng, Sancheng
    Niu, Jianwei
    Yu, Shui
    Wang, Cuirong
    NEUROCOMPUTING, 2021, 428 : 195 - 205
  • [28] Exploring Weakly Supervised Latent Sentiment Explanations for Aspect-level Review Analysis
    Fang, Lei
    Huang, Minlie
    Zhu, Xiaoyan
    PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13), 2013, : 1057 - 1066
  • [29] Aspect-level sentiment analysis for based on joint aspect and position hierarchy attention mechanism network
    Shao, Dangguo
    An, Qing
    Huang, Kun
    Xiang, Yan
    Ma, Lei
    Guo, Junjun
    Yin, Runda
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 42 (03) : 2207 - 2218
  • [30] A complete framework for aspect-level and sentence-level sentiment analysis
    Rim Chiha
    Mounir Ben Ayed
    Célia da Costa Pereira
    Applied Intelligence, 2022, 52 : 17845 - 17863