An Effective Sarcasm Detection Approach Based on Sentimental Context and Individual Expression Habits

被引:30
作者
Du, Yu [1 ]
Li, Tong [1 ]
Pathan, Muhammad Salman [1 ]
Teklehaimanot, Hailay Kidu [1 ]
Yang, Zhen [1 ]
机构
[1] Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
关键词
Sarcasm detection; Convolutional neural network; Attention mechanism; Sentimental context; Expression habit;
D O I
10.1007/s12559-021-09832-x
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sarcasm is common in social media, and people use it to express their opinions with stronger emotions indirectly. Although it belongs to a branch of sentiment analysis, traditional sentiment analysis methods cannot identify the rhetoric of irony as it requires a significant amount of background knowledge. Existing sarcasm detection approaches mainly focus on analyzing the text content of sarcasm using various natural language processing techniques. It is argued herein that the essential issue for detecting sarcasm is examining its context, including sentiments of texts that reply to the target text and user's expression habit. A dual-channel convolutional neural network is proposed that analyzes not only the semantics of the target text, but also its sentimental context. In addition, SenticNet is used to add common sense to the long short-term memory (LSTM) model. The attention mechanism is then applied to take the user's expression habits into account. A series of experiments were carried out on several public datasets, the results of which show that the proposed approach can significantly improve the performance of sarcasm detection tasks.
引用
收藏
页码:78 / 90
页数:13
相关论文
共 39 条
  • [1] Amir S., 2016, P 20 SIGNLL C COMP N, P167, DOI 10.18653/v1/K16-1017
  • [2] [Anonymous], 2013, P WORKSHOP LANGUAGE
  • [3] Multitask Learning for Fine-Grained Twitter Sentiment Analysis
    Balikas, Georgios
    Moura, Simon
    Amini, Massih-Reza
    [J]. SIGIR'17: PROCEEDINGS OF THE 40TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2017, : 1005 - 1008
  • [4] Bamman D., 2015, P INT AAAI C WEB SOC, P574, DOI [10.1609/icwsm.v9i1.14655, DOI 10.1609/ICWSM.V9I1.14655]
  • [5] Parsing-based Sarcasm Sentiment Recognition in Twitter Data
    Bharti, Santosh Kumar
    Babu, Korra Sathya
    Jena, Sanjay Kumar
    [J]. PROCEEDINGS OF THE 2015 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2015), 2015, : 1373 - 1380
  • [6] SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis
    Cambria, Erik
    Li, Yang
    Xing, Frank Z.
    Poria, Soujanya
    Kwok, Kenneth
    [J]. CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 105 - 114
  • [7] Cambria E, 2018, AAAI CONF ARTIF INTE, P1795
  • [8] Affective Computing and Sentiment Analysis
    Cambria, Erik
    [J]. IEEE INTELLIGENT SYSTEMS, 2016, 31 (02) : 102 - 107
  • [9] Cambria E, 2015, AAAI CONF ARTIF INTE, P508
  • [10] A comparison between semi-supervised and supervised text mining techniques on detecting irony in greek political tweets
    Charalampakis, Basilis
    Spathis, Dimitris
    Kouslis, Elias
    Kermanidis, Katia
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2016, 51 : 50 - 57