Sentiment Classifier: Logistic Regression for Arabic Services' Reviews in Lebanon

被引：0
|
作者：
Al Omari, Marwan [1 ]
Al-Hajj, Moustafa [1 ]
Hammami, Nacereddine [2 ]
Sabra, Amani [1 ]
机构：
[1] Lebanese Univ, Ctr Language Sci & Commun, Beirut, Lebanon
[2] Jouf Univ, Coll Comp & Informat Sci, Aljouf, Saudi Arabia
来源：
2019 INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCES (ICCIS) | 2019年
关键词：
Arabic natural language; Services' reviews; Logistic regression; Supervised machine learning; Arabic sentiment analysis;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper proposes a logistic regression approach paired with term and inverse document frequency (TF*IDF) for Arabic sentiment classification on services' reviews in Lebanon country. Reviews are about public services, including hotels, restaurants, shops, and others. We collected manually from Google reviews and Zomato, which have reached to 3916 reviews. Experiments show three core findings: 1) The classifier is confident when used to predict positive reviews. 2) The model is biased on predicting reviews with negative sentiment. Finally, the low percentage of negative reviews in the corpus contributes to the diffidence of logistic regression model.
引用
收藏
页码：168 / 172
页数：5
相关论文
共 50 条
  • [1] Investigation on Sentiment Analysis for Arabic Reviews
    Elnagar, Ashraf
    [J]. 2016 IEEE/ACS 13TH INTERNATIONAL CONFERENCE OF COMPUTER SYSTEMS AND APPLICATIONS (AICCSA), 2016,
  • [2] Enhanced Classification of Sentiment Analysis of Arabic Reviews
    Alnemer, Loai
    Alammouri, Bayan
    Alsakran, Jamal
    El Ariss, Omar
    [J]. ADVANCES IN INTERNET, DATA AND WEB TECHNOLOGIES, 2019, 29 : 210 - 220
  • [3] An Unsupervised Sentiment Classifier on Summarized or Full Reviews
    Pera, Maria Soledad
    Qumsiyeh, Rani
    Ng, Yiu-Kai
    [J]. WEB INFORMATION SYSTEM ENGINEERING-WISE 2010, 2010, 6488 : 142 - 156
  • [4] ν-soft margin logistic regression classifier
    [J]. Huang, Chengquan (hcq863@163.com), 1600, Science Press (38):
  • [5] Morphology Based Arabic Sentiment Analysis of Book Reviews
    El Ariss, Omar
    Alnemer, Loai M.
    [J]. COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, CICLING 2017, PT II, 2018, 10762 : 115 - 128
  • [6] Rating Predictor: Sentiment Analysis of Product Reviews in Arabic
    Harrage, Fouzi
    Alsalman, Abdulmalik
    Alqahtani, Alaa
    [J]. 2018 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP), 2018, : 44 - 49
  • [7] Multi-Way Sentiment Classification of Arabic Reviews
    Al Shboul, Bashar
    Al-Ayyoub, Mahmoud
    Jararweh, Yaser
    [J]. 2015 6TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION SYSTEMS (ICICS), 2015, : 206 - 211
  • [8] Sentiment Analysis Using Multinomial Logistic Regression
    Ramadhan, W. P.
    Novianty, Astri
    Setianingsih, Casi
    [J]. 2017 INTERNATIONAL CONFERENCE ON CONTROL, ELECTRONICS, RENEWABLE ENERGY AND COMMUNICATIONS (ICCREC), 2017, : 46 - 49
  • [9] Arabic Language Sentiment Analysis on Health Services
    Alayba, Abdulaziz M.
    Palade, Vasile
    England, Matthew
    Iqbal, Rahat
    [J]. 2017 1ST INTERNATIONAL WORKSHOP ON ARABIC SCRIPT ANALYSIS AND RECOGNITION (ASAR), 2017, : 114 - 118
  • [10] Feature-Based Sentiment Analysis in Online Arabic Reviews
    Abd-Elhamid, Laila
    Elzanfaly, Doaa
    Eldin, Ahmed Sharaf
    [J]. PROCEEDINGS OF 2016 11TH INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING & SYSTEMS (ICCES), 2016, : 260 - 265
12345