Satire identification in Turkish news articles based on ensemble of classifiers

被引:34
|
作者
Onan, Aytug [1 ]
Tocoglu, Mansur Alp [2 ]
机构
[1] Izmir Katip Celebi Univ, Fac Engn & Architecture, Dept Comp Engn, Izmir, Turkey
[2] Manisa Celal Bayar Univ, Fac Technol, Dept Software Engn, Manisa, Turkey
关键词
Satire detection; figurative language; machine learning; classifier ensembles;
D O I
10.3906/elk-1907-11
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Social media and microblogging platforms generally contain elements of figurative and nonliteral language, including satire. The identification of figurative language is a fundamental task for sentiment analysis. It will not be possible to obtain sentiment analysis methods with high classification accuracy if elements of figurative language have not been properly identified. Satirical text is a kind of figurative language, in which irony and humor have been utilized to ridicule or criticize an event or entity. Satirical news is a pervasive issue on social media platforms, which can be deceptive and harmful. This paper presents an ensemble scheme for satirical news identification in Turkish news articles. In the presented scheme, linguistic and psychological feature sets have been utilized to extract the feature sets (i.e. linguistic, psychological, personal, spoken categories, and punctuation). In the classification phase, accuracy rates of five supervised learning algorithms (i.e. naive Bayes algorithm, logistic regression, support vector machines, random forest, and k-nearest neighbor algorithm) with three widely utilized ensemble methods (i.e. AdaBoost, bagging, and random subspace) have been considered. Based on the results, we concluded that the random forest algorithm yielded the highest performance, with a classification accuracy of 96.92% for satire detection in Turkish. For deep learning-based architectures, we have achieved classification accuracy of 97.72% with the recurrent neural network architecture with attention mechanism.
引用
收藏
页码:1086 / 1106
页数:21
相关论文
共 50 条
  • [11] Towards Ensemble Learning for Tracking Food Insecurity From News Articles
    Lukyamuzi, Andrew
    Ngubiri, John
    Okori, Washington
    INTERNATIONAL JOURNAL OF SYSTEM DYNAMICS APPLICATIONS, 2020, 9 (04) : 129 - 142
  • [12] Cross-Entropy Based Ensemble Classifiers
    Lafratta, Giovanni
    DECISION ECONOMICS, IN COMMEMORATION OF THE BIRTH CENTENNIAL OF HERBERT A. SIMON 1916-2016 (NOBEL PRIZE IN ECONOMICS 1978), 2016, 475 : 43 - 47
  • [13] An Ensemble Method Based on Evolving Classifiers: eStacking
    Antonio Iglesias, Jose
    Ledezma, Agapito
    Sanchis, Araceli
    2014 IEEE SYMPOSIUM ON EVOLVING AND AUTONOMOUS LEARNING SYSTEMS (EALS), 2014, : 124 - 131
  • [14] Greedy optimization classifiers ensemble based on diversity
    Mao, Shasha
    Jiao, L. C.
    Xiong, Lin
    Gou, Shuiping
    PATTERN RECOGNITION, 2011, 44 (06) : 1245 - 1261
  • [15] Span identification and technique classification of propaganda in news articles
    Wei Li
    Shiqian Li
    Chenhao Liu
    Longfei Lu
    Ziyu Shi
    Shiping Wen
    Complex & Intelligent Systems, 2022, 8 : 3603 - 3612
  • [16] Span identification and technique classification of propaganda in news articles
    Li, Wei
    Li, Shiqian
    Liu, Chenhao
    Lu, Longfei
    Shi, Ziyu
    Wen, Shiping
    COMPLEX & INTELLIGENT SYSTEMS, 2022, 8 (05) : 3603 - 3612
  • [17] Ensemble of Classifiers Based on Simple Granules of Knowledge
    Artiemjew, Piotr
    INFORMATION AND SOFTWARE TECHNOLOGIES (ICIST 2017), 2017, 756 : 343 - 350
  • [18] An ensemble of SVM classifiers based on gene pairs
    Tong, Muchenxuan
    Liu, Kun-Hong
    Xu, Chungui
    Ju, Wenbin
    COMPUTERS IN BIOLOGY AND MEDICINE, 2013, 43 (06) : 729 - 737
  • [19] Ensemble Method Based on Individual Evolving Classifiers
    Antonio Iglesias, Jose
    Ledezma, Agapito
    Sanchis, Araceli
    PROCEEDINGS OF THE 2013 IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS (EAIS), 2013, : 56 - 61
  • [20] Text Authorship Identification Based On Ensemble Learning and Genetic Algorithm Combination in Turkish Text
    Gullu, Merve
    Polat, Huseyin
    JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2021,