Sentiment Analysis of Student's Facebook Posts

被引:0
作者
Iram, Ateya [1 ]
机构
[1] Natl Coll Business Adm & Econ, Lahore, Pakistan
来源
INTELLIGENT TECHNOLOGIES AND APPLICATIONS, INTAP 2018 | 2019年 / 932卷
关键词
Sentiment analysis; Facebook; NLP; Sentiment classification; TF-IDF; SentiWordNet;
D O I
10.1007/978-981-13-6052-7_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Students are the major part of the colleges/universities and a beneficial of the institutions. Students reviews and opinions are important to improve the institutional problem, matters, and issues. The success of any college/university is to increase the students' satisfaction level and it's good for increasing the ranking of the institution. Its paper target the students' sentiments post on Facebook colleges/university groups to express their behaviors, opinions, and views related curriculum and extra curriculum activities. Developing an automated system, use the students' post of the Facebook group to implement the Novel approach. This paper uses the dataset that is based on the issues of the National College of Business Administration & Economics. This research work provides the automated system to detect the students' post of related issues is positive, negative and neutral. Developing tool provides the best outcomes to improve the related issues, matters and institution's policies.
引用
收藏
页码:86 / 97
页数:12
相关论文
共 24 条
  • [1] Social Networks' Facebook' Statutes Updates Mining for Sentiment Classification
    Akaichi, Jalel
    [J]. 2013 ASE/IEEE INTERNATIONAL CONFERENCE ON SOCIAL COMPUTING (SOCIALCOM), 2013, : 886 - 891
  • [2] [Anonymous], 2013, IISA, DOI DOI 10.1109/IISA.2013.6623713
  • [3] Developing Corpora for Sentiment Analysis: The Case of Irony and Senti-TUT
    Bosco, Cristina
    Patti, Viviana
    Bolioli, Andrea
    [J]. IEEE INTELLIGENT SYSTEMS, 2013, 28 (02) : 55 - 63
  • [4] Cheng-Yu Lu, 2010, Proceedings 2010 IEEE 13th International Conference on Computational Science and Engineering (CSE 2010), P295, DOI 10.1109/CSE.2010.44
  • [5] Learning Semantic Similarity for Very Short Texts
    De Boom, Cedric
    Van Canneyt, Steven
    Bohez, Steven
    Demeester, Thomas
    Dhoedt, Bart
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOP (ICDMW), 2015, : 1229 - 1234
  • [6] He ZS, 2007, PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, P2936
  • [7] Ingale S. D., 2015, INT J ENG RES TECHNO, V4, P646
  • [8] Jamal Noraini, 2012, Journal of Computer Science, V8, P1441
  • [9] Kaur J., 2014, INT J COMPUT APPL, V101
  • [10] Kouloumpis E., 2011, TWITTER SENTIMENT AN, P538