Analisis Sentimen pada Twitter menggunakan Word Embedding dengan Pendekatan Word2Vec
Abstract
In this day and age, the use of social media is familiar to some circles. The existence of social media can be analyzed for certain interests. This analysis can also be carried out for the benefit of knowing the opinions or sentiments that contain it. Therefore, a sentiment analysis is needed to get a classification of existing opinions. The use of sentiment analysis cannot be separated from the document or text representation stage. This usually takes the form of the bag of word (BOW). However, BOW has a weakness, namely it produces a lot of features so that the classification accuracy results are less than optimal. Therefore we need the Word Embedding method to represent documents in vector form. The use of this method results in fewer features so that data training time can be shorter. Apart from that, the syntax and semantics of the words that compose the tweet are also considered. So, Word Embedding produces meaningful vectors.
Downloads
References
S. Vanaja, “Aspect-Level Sentiment Analysis on E-Commerce Data,” 2018 Int. Conf. Inven. Res. Comput. Appl., no. Icirca, pp. 1275–1279, 2018.
A. Yousefpour, R. Ibrahim, and H. N. A. Hamed, “Ordinal-based and frequency-based integration of feature selection methods for sentiment analysis,” Expert Syst. Appl., vol. 75, pp. 80–93, 2017.
W. Medhat, A. Hassan, and H. Korashy, “Sentiment analysis algorithms and applications: A survey,” Ain Shams Eng. J., vol. 5, pp. 1093–1113, 2014.
R. A. Stein, P. A. Jaques, and J. F. Valiati, “An Analysis of Hierarchical Text Classification Using Word Embeddings,” Inf. Sci. (Ny)., vol. 471, pp. 216–232, 2019.
F. S. Nurfikri, M. S. Mubarok, and A. Adiwijaya, “News topic classification using mutual information and Bayesian network,” in 6th International Conference on Information and Communication Technology, 2018, vol. 0, no. c, pp. 162–166.
M. J. Tian, R. Y. Cui, and Z. H. Huang, “Automatic Extraction Method for Specific Domain Terms Based on Structural Features and Mutual Information,” Proc. - 2018 5th Int. Conf. Inf. Sci. Control Eng. ICISCE 2018, pp. 147–150, 2019.
M. Te Wu, “Artifact reduction based on mutual information measures,” in 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, 2016, pp. 1868–1871.
A. Khatua, A. Khatua, and E. Cambria, “A Tale of Two Epidemics: Contextual Word2Vec for Classifying Twitter Streams During Outbreaks,” Inf. Process. Manag., vol. 56, no. 1, pp. 247–257, 2019.
F. Ali et al., “Transportation sentiment analysis using word embedding and ontology-based topic modeling,” Knowledge-Based Syst., vol. 174, pp. 27–42, 2019.
J. W. Creswell, Research design : Qualitative, Quantitative, and Mixed Methods Approaches, 4th ed., vol. 112, no. 483. Los Angeles, USA: Sage, 2014.
