Text Mining pada Sosial Media untuk Mendeteksi Emosi Pengguna Menggunakan Metode Support Vector Machine dan K-Nearest Neighbour
Twitter social networking and microblog services that allow users to send and read text-based messages up to 140 characters, known as tweets. A text in a tweet does not only convey information from an information, but also contains information about human behavior including emotions. To detect the emotion of the text on Twitter social media services with unstructured data, it is necessary to do text analysis, one of them is by using Text Mining. Text mining tries to extract useful information from data sources through identification and exploration of an interesting pattern. Data sources are a collection of documents and interesting patterns that are not found in the form of record databases, but in unstructured text data. In this study proposes to do text mining research on Social Media to detect user emotions. Text-based emotional detection can be used in business, education, psychology, and any other field that is most important for understanding and interpreting emotions. From the tests carried out by the Support Vector Machine and K-Nearest Neighbor methods can produce an average value of precision of 0.45640904478933. Recall value is 0.50199332258158 and the accuracy value is 0.8140589569161 while from the K-Nearest Neighbor method the average value of precision is 0.34210487225193. Recall value is 0.45954538381009 and the accuracy value is 0.79705215419501. the results of testing with the SVM-KNN method showed that the suitability of emotional classification was better than the K-Nearest Neighbor method of the whole emotional categories.
 V. P. Haji Binali, Chen Wu, “Computational Approaches for Emotion Detection in Text,” IEEE Int. Conf. Digit. Ecosyst. Technol. (IEEE DEST 2010), 2010.
 C. G. Patil and S. S. Patil, “Use of Porter Stemming Algorithm and SVM for Emotion Extraction from News Headlines,” Int. J. Electron. Commun. Soft Comput. Sci. Eng., vol. 2, no. 7, pp. 2277–9477, 2013.
 Arifin, “Classification of Emotions in Indonesian TextsUsing K-NN Method,” Int. J. Inf. Electron. Eng., 2012.
 C. Cortes and V. Vapnik, “Support vector machine,” Mach. Learn., pp. 1303–1308, 1995.
 R. I. Ndaumanu and M. R. Arief, Kusrini, “Analisis Prediksi Tingkat Pengunduran Diri Mahasiswa dengan Metode K-Nearest Neighbor,” Jatisi, vol. 1, no. 1, pp. 1–15, 2014.
 I. N. W. Tirtayani, Luh Ayu, Noce Maylani Asril, “Perkembangan Sosial Emosional pada Anak Usia Dini,” Univ. Terbuka Repos., pp. 1–43, 2013.
 N. G. Yudiarta, M. Sudarma, and W. G. Ariastina, “Pengelompokan Berita Pada Unstructured Textual Data,” vol. 17, no. 3, pp. 339–344, 2018.
 A. P. Sujana, “Memanfaatkan Big Data Untuk Mendeteksi Emosi,” Tek. Komput. Unikom, vol. 2, no. 2, pp. 1–4, 2013.
 N. L. Ratniasih, M. Sudarma, N. Gunantara, and A. A. U. Sistem, “Penerapan Text Mining dalam Spam Filtering untuk Aplikasi Chat,” Teknol. Elektro, vol. 16, no. 3, pp. 13–18, 2017.
 M. Adriani, J. Asian, B. Nazief, and H. E. Williams, “Stemming Indonesian : A Confix Stripping Approach,” ACM Trans. Asian Lang. Inf. Process., vol. 6, no. 4, pp. 1–33, 2007.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License