Sarcasm Detection on Twitter Using Gated Recurrent Units Method

Maulidan Maulidan, Khadafi Khadafi, Huzaeni Huzaeni

Abstract


Sarcasm is often used as a tool to achieve humorous effects, convey criticism in an entertaining way, or convey messages with irony. Social media, especially Twitter, has become a significant platform for expression and information exchange, where sarcasm is often used as a means of communication. This study focuses on the use of Gated Recurrent Unit (GRU), a type of unit in a recurrent neural network (RNN), to detect sarcastic sentences on Twitter. The data used in this study were taken from sources that had been used in previous tests, totaling 10,000 data, which were divided into two classes: sarcastic and non-sarcastic. As much as 80% of this data was used as training data, while the remaining 20% was used as test data. The test results showed that the GRU model was able to achieve an accuracy of 73% using the confusion matrix and 74% using the K-Fold Cross Validation method. This shows the model's ability to classify sarcastic and non-sarcastic sentences effectively.

References


A. Kumar, V. T. Narapareddy, V. A. Srikanth, A. Malapati, and L. B. M. Neti, “Sarcasm Detection Using Multi-Head Attention Based Bidirectional LSTM,†IEEE Access, vol. 8, pp. 6388–6397, 2020, doi: 10.1109/ACCESS.2019.2963630.

M. Bouazizi and T. Otsuki, “A Pattern-Based Approach for Sarcasm Detection on Twitter,†IEEE Access, vol. 4, pp. 5477–5488, 2016, doi: 10.1109/ACCESS.2016.2594194.

Z. Doshi, S. Nadkarni, K. Ajmera, and N. Shah, “TweerAnalyzer: Twitter Trend Detection and Visualization,†2017 Int. Conf. Comput. Commun. Control Autom. ICCUBEA 2017, 2017, doi: 10.1109/ICCUBEA.2017.8463951.

D. M. Ashok, A. Nidhi Ghanshyam, S. S. Salim, D. Burhanuddin Mazahir, and B. S. Thakare, “Sarcasm detection using genetic optimization on LSTM with CNN,†2020 Int. Conf. Emerg. Technol. INCET 2020, pp. 3–6, 2020, doi: 10.1109/INCET49848.2020.9154090.

T. Ishitaki, R. Obukata, T. Oda, and L. Barolli, “Application of deep recurrent neural networks for prediction of user behavior in tor networks,†Proc. - 31st IEEE Int. Conf. Adv. Inf. Netw. Appl. Work. WAINA 2017, pp. 238–243, 2017, doi: 10.1109/WAINA.2017.63.

S. A. Al-Ghamdi, J. Khabti, and H. S. Al-Khalifa, “Exploring NLP web APIs for building Arabic systems,†2017 12th Int. Conf. Digit. Inf. Manag. ICDIM 2017, vol. 2018-Janua, no. Icdim, pp. 175–178, 2017, doi: 10.1109/ICDIM.2017.8244649.

G. A. J. Satvika, S. M. Nasution, and R. A. Nugrahaeni, “Determination of the Best Vehicle Pathway with Classification of Data Mining Twitter using K-Nearest Neighbor,†2018 Int. Conf. Inf. Technol. Syst. Innov. ICITSI 2018 - Proc., pp. 72–76, 2018, doi: 10.1109/ICITSI.2018.8695947.

Jahan, S. S. (2014). Human Resources Information System (HRIS): A theoretical perspective. Journal of Human Resource and Sustainability Studies, 02(02), 33–39. https://doi.org/10.4236/jhrss.2014.22004.

Niu, Z., Yu, Z., Tang, W., Wu, Q., & Reformat, M. (2020). Wind power forecasting using attention-based gated recurrent unit network. Energy, 196, 117081. https://doi.org/10.1016/j.energy.2020.117081.

Sherstinsky, A. (2020). Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Physica D Nonlinear Phenomena, 404, 132306. https://doi.org/10.1016/j.physd.2019.132306.


Refbacks

  • There are currently no refbacks.


Indexing :

Creative Commons License
Journal of Informatics Engineering and Software Applications (JIEngS) licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.