A Systematic Literature Review of Short Text Classification on Twitter
Abstract
Twitter is a microblogging service that allows people to communicate via messages containing only 140 characters briefly. With these limits, Twitter can be categorized as a short text document. And with the limited number of words makes the tweet it difficult to classify. This study aims to generate classification maps and find out the best method to classify short text documents, especially on Twitter by analyzing literary data using a systematic literature review analysis method. The process of collecting literature data is done by searching on several digital libraries with search strings that have been made based on the existing research question with the publication limit between 2013-2017. The results of this research indicate that from 1253 literature, 41 works of literature deserve to be analyzed. And based on 41 existing literature found that there are 21 methods of classification used for twitter classification. With the most widely used method is Support Vector Machine (SVM) and the best method is Word2Vec Logistic Regression with an accuracy of 95,8%.
Keywords: short text, systematic literature review, mapping research, classification, twitter
References
[1] Han, Jiawei dkk. 2012. Data Mining Concepts and Techniques. Ed ke-3. USA: Elsevier Inc
[2] . Wahono, R. S. (2015). A Systematic Literature Review of Software Defect Prediction: Research Trends, Datasets, Methods and Frameworks. Journal of Software Engineering, 1:1
[3] Kitchenham&Charters. (2007). Guidelines in Performing Systematic Literature Reviews in Software Engineering. EBSE Technical Report 33(5): 20.
[4] Hall, T., Beecham S., Bowes D., Gray D., & Counsell, S. (2012). A Systematic Literature Review on Fault Prediction Performance in Software Engineering. IEEE Transactions on Software Engineering, 38:1276-1304.
[5] Leedy, Paul.D. & Jeanne.E. Ormrod. (2014). Practical Research: Planning and Design a Research. Ed ke-10. London: Pearson Education Limited.
[6] Heck, P. & Zaidman, A. (2016). A Systematic Literature Review on Quality Criteria for Agile Requirements Specifications. Link Springer, 26:127-160.
[7] Paris, D. L., Bahari, M., Iahad, N., & Ismail, W. (2016). Systematic Literature Review of e-Commerce Implementations Studies. Search EBSCOhost, 89:422-438.
[8] Wen, J., Li, S., Lin, Z., Hu, Y., & Huang, C. (2012). Systematic Literature Review of Machine Learning (ML) Based Software Development Effort Estimation Models. Search EBSCOhost, 54:41-59.