Lexicon-based Emotion Detection for Academic Questionnaire Results
Abstract
Tujuan: Penelitian ini bertujuan menerapkan metode deteksi emosi pada teks komentar mahasiswa hasil kuesener berbasis pada leksikon emosi. Label emosi dari komentar akan meningkatkan akurasi dari hasil analisis kuesener. Tujuan lain dari penelitian ini adalah melihat sejauh mana efektivitas leksikon emosi Emolex untuk deteksi emosi teks kuesener akademis.
Metode: Data penelitian berasal dari komentar dan saran mahasiswa pada kuesener evaluasi pembelajaran pada IST AKPRIND tahun 2014-2017 sebanyak 3.975 komentar. Jenis emosi yang dideteksi adalah 8 jenis emosi, yaitu marah, antisipasi, jijik, takut, bahagia, sedih , terkejut dan yakin. Leksikon emosi yang digunakan adalah NRC Emolex. Langkah pertama deteksi setelah tahap pre-processing adalah ekstrak fitur emosi menggunakan daftar leksikon emosi. Langkah kedua adalah deteksi emosi dengan cara menghitung bobot terbesar dari fitur emosi yang terekstrak sebagai label emosi bagi komentar tersebut.
Hasil: Hasil penelitian menunjukkan bahwa dari seluruh data yang dideteksi, 46,7% dapat diketahui label emosinya. Dari yang diketahui label emosinya 3 prosentase tertinggi ada pada label Sadness (18,5%), Joy(17,1%) dan Fear (14,0%). Dari penelitian terungkap bahwa kinerja emolex untuk deteksi emosi masih belum memuaskan. Hal ini sangat mungkin disebabkan karena baru 37% pustaka Emolex memiliki label emosi.
State of the art: Ditemukan kelemahan leksikon NRC Emolex sebagai hasil translate dari bahasa inggris antara lain, banyak leksikon belum diberikan label emosi dan efek translate menjadi dua atau tiga kata dalam bahasa Indonesia sehinggat tidak dapat digunakan.
Keywords
Full Text:
PDFReferences
R. Plutchik, The Psychology and Biology of Emotion. New York: Harper Collins Publisher, 1994.
S. M. Mohammad, “Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text,” Emot. Meas., pp. 201–237, 2015, doi: 10.1016/B978-0-08-100508-8.00009-6.
F. Celli and L. Rossi, “The role of Emotional Stability in Twitter Conversations,” Proc. Work. Semant. Anal. Soc. Media, conjunction with EACL 2012, pp. 10–17, 2012, [Online]. Available: http://aclweb.org/anthology-new/W/W12/W12-0602.pdf.
R. A. Calvo and S. Mac Kim, “Emotions in text : dimensional and categorical models,” Comput. Intell., vol. 29, no. 3, pp. 527–543, 2013.
F. Greaves, C. Excellence, D. Ramirez-cano, and L. J. Donaldson, “Use of Sentiment Analysis for Capturing Patient Experience From Free-Text Comments Posted Online,” J. Med. Internet Res., vol. 15, no. 11, pp. 145–152, 2013, doi: 10.2196/jmir.2721.
B. Liu, Sentiment Analysis and Opinion Mining, no. May. Morgan & Claypool Publisher, 2012.
V. Anusha and B. Sandya, “A learning based emotion classifier with semantic text processing,” Adv. Intell. Syst. Comput., vol. 320, pp. 371–382, 2015.
S. Poria, A. Gelbukh, D. Das, and S. Bandyopadhyay, “Fuzzy Clustering for Semi-Supervised Learning — Case study : Construction of an Emotion Lexicon,” in Mexican International Conference on Artificial Intelligence (MICAI 2012) Advances in Artificial Intelligence, 2012, pp. 23–27.
M. Abdullah, M. Hadzikadic, S. Shaikh, and N. Carolina, “SEDAT : Sentiment and Emotion Detection in Arabic Text using CNN-LSTM Deep Learning,” in in Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, 2018, pp. 835–840.
P. Ekman, “An Argument for Basic Emotions,” Cogn. Emot., vol. 4, no. 3, pp. 169–200, 1992.
B. Agarwal, N. Mittal, P. Bansal, and S. Garg, “Sentiment Analysis Using Common-Sense and Context Information Sentiment Analysis Using Common-Sense and,” Comput. Intell. Neurosci., vol. 2015, no. 6, pp. 715–730, 2015, doi: 10.1155/2015/715730.
M. Vania, C., Ibrahim, M., & Adriani, “Sentiment Lexicon Generation for an Under-Resourced Language,” Int. J. Comput. Linguist. Appl., vol. 5, no. 1, pp. 59–72, 2014.
J. Bata, Sunyoto, and Pranowo, “Leksikon untuk deteksi emosi dari teks bahasa indonesia,” in Seminar Nasional Informatika 2015 (semnasIF 2015), 2015, vol. 2015, no. November, pp. 195–202.
P. R. Shaver, U. Murdaya, and R. C. Fraley, “Structure of the Indonesian emotion lexicon,” Asian J. Soc. Psychol., vol. 4, no. 3, pp. 201–224, 2001.
S. M. Mohammad and P. D. Turney, “Crowdsourcing a Word – Emotion Association Lexicon,” Comput. Intell., vol. 29, no. 3, pp. 436–465, 2013.
M. AL-Al’abeda and M. Al-ayyoub, “A Lexicon-Based Approach for Emotion Analysis of Arabic Social Media A Lexicon-Based Approach for Emotion Analysis of Arabic Social Media Content,” in Proceedings of the International Computer Sciences and Informatics Conference (ICSIC 2016), 2016, pp. 343–351.
S. Goyal and N. Tiwari, “EMOTION RECOGNITION : A LITERATURE SURVEY,” Int. J. Technol. Res. Eng., vol. 4, no. 9, pp. 1502–1524, 2017.
S. Grover and A. Verma, “Design for emotion detection of punjabi text using hybrid approach,” in Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016, 2016, no. 2, pp. 2019–2021.
A. S. Aribowo, S. Khomsah, U. Pembangunan, N. Veteran, S. Data, and I. Artikel, “Implementation Of Text Mining For Emotion Detection Using The Lexicon Method ( Case Study : Tweets About Covid-19 ),” vol. 18, no. 1, pp. 49–60, 2021, doi: 10.31515/telematika.v18i1.4341.
Muljono, A. S. Winarsih, and C. Supriyanto, “Evaluation of classification methods for Indonesian text emotion detection,” in Proceedings - 2016 International Seminar on Application of Technology for Information and Communication, ISEMANTIC 2016, 2016, pp. 130–133.
A S Aribowo, H. Basiron, N. S. Herman, and S. Khomsah, “Fanaticism Category Generation Using Tree-Based Machine Learning Method Fanaticism Category Generation Using Tree-Based Machine Learning Method,” J. Phys. Conf. Ser, 2020, doi: 10.1088/1742-6596/1501/1/012021.
F. Krebs, B. Lubascher, T. Moers, and P. Schaap, “Social Emotion Mining Techniques for Facebook Posts Reaction Prediction,” in International Conference on Agents and Artificial Intelligence, 2017, vol. 2, no. 1, pp. 211–220.
S. X. Mashal and K. Asnani, “Emotion intensity detection for social media data,” in Proc. Int. Conf. Computing Methodologies and Communication ( ICCMC 2017), 2017, pp. 155–158.
A. N. Rohman, E. Utami, and S. Raharjo, “Deteksi Emosi Media Sosial Menggunakan Pendekatan Leksikon dan Natural Language Processing,” Eksplora Informartika, 2019. .
M. Saif, “NRC Emotion Lexicon.” https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm.
Refbacks
- There are currently no refbacks.