Detection of Sentiment Analysis in Social Media using Deep Learning
M Srilakshmi Preethi1, S Thabassum Khan2, D Divya Shree3
1M Srilakshmi Preethi*, Assistant Professor, Dept. of CSE, Sri Venkateswara College of Engineering, Tirupati, India.
2SThabassum Khan, Assistant Professor, Dept. of Information Technology, Sri Venkateswara Engineering College, Tirupati, India.
3D Divya Shree, Assistant Professor, Dept. of Computer Science & System Engineering, Sree Vidyanikethan Engineering College, Tirupati, India.
Manuscript received on April 02, 2020. | Revised Manuscript received on April 18, 2020. | Manuscript published on May 30, 2020. | PP: 636-643 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1927059120/2020©BEIESP | DOI: 10.35940/ijrte.A1927.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: With the rapid climb of web page from social media, such studies as online opinion mining or sentiment analysis of text have started receiving attention from government, industry, and academic sectors. In recent years, sentiment analysis has not only emerged under knowledge fusion within the big data era, but has also become a well-liked research topic within the area of AI and machine learning. This study used the Military life PTT board of Taiwan’s largest online forum because the source of its experimental data. the aim of this study was to construct a sentiment analysis framework and processes for social media so as to propose a self-developed military sentiment dictionary for improving sentiment classification and analyze the performance of various deep learning models with various parameter calibration combinations. The experimental results show that the accuracy and F1-measure of the model that mixes existing sentiment dictionaries and therefore the self-developed military sentiment dictionary are better than the results from using existing sentiment dictionaries only. Furthermore, the prediction model trained using the activation function, Tanh, and when the amount of Bi-LSTM network layers is 2, the accuracy and F1-measure have a good better performance for sentiment classification.
Keywords: Sentiment analysis, Social media, Deep learning, LSTM, Bi-LSTM, Machine Learning.
Scope of the Article: Deep Learning