The objective of this project is to determine whether the machine learning model can effectively predict whether a sentiment is predominantly positive or negative by analyzing tweets about IKN (Ibu Kota Negara), the New National Capital City project in Indonesia. Data is obtained through crawling Twitter data related to IKN discussion topics. Furthermore, the data is analyzed using the SVM classification method by combining it with the Query Expansion technique to produce better model performance.
Files Description:
- Dataset: a folder containing the dataset that will be used in the project. The dataset consists of 2177 tweets about IKN that are categorized into positive or negative sentiments.
- Hasil: a folder containing results after cleaning, normalization, pre-processing, and stop word removal of the dataset.
- Kamus: a folder containing a List of Opinion Words (positive/negative) in Bahasa Indonesia. Originated by Liu's Opinion Words list with modification/translation to Indonesia.
Python using Google Collab
Syenira Sheila
- LinkedIn: @SyeniraSheila
- Github: @syenirasheila
Hopefully, this project can be valuable and beneficial for the advancement of Technology and Information, and if it's been useful to you, please give it a ⭐️ on this repository! Thank you 😃
- Wahid, D. H., & Azhari, S. N. (2016). Peringkasan Sentimen Esktraktif di Twitter Menggunakan Hybrid TF-IDF dan Cosine Similarity. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 10(2), 207-218.
- Liu, Bing, Hu, Minqing, and Cheng, Junsheng (2005). "Opinion Observer: Analyzing and Comparing Opinions on the Web." Proceedings of the 14th International World Wide Web Conference (WWW-2005), May 10-14, Chiba, Japan.