Global Journal of Computer Science and Technology, D: Neural & Artificial Intelligence, Volume 22 Issue 1

impeccable credentials and history ✌ ! 5 The people of UP are urging for relief from gundarj, terror & hypocrisy of Saffron reign ☹ Negative 6 Paranoid, vindictive government will not let farmers survive ☹ . Through attacks on farmers the government has finally declared that there is emergency in India now Negative #FarmersParliament 7 Farmers will discuss about APMC mandis in today's Parliament of farmers . Groups of 200 farmers will protest outside the Parliament every day , during the monsoon session, to strengthen the voice in the temple of Democracy ☹ Negative #FarmersParliament From the above table, we observe that people talk about various events and express their sentiment in social media. This is really an alternate to traditional polling and cost effective solution for decision makers to understand the situation and respond to any emerging crisis. V. C onclusion and F uture work The proposed method accomplished superior performance in terms of sentiment classification of eWOMs according to polarity. The major challenge in using the NLP tools for understanding the social media messages is eliminated by our two-step methodology namely feature extractor and CNN. By using a centralized sentiment analysis system, commercial organizations can improve accuracy and gain better insights while analyzing customer feedback and complaints. The overall benefits of AI based sentiment analysis include: Sorting Data at Scale: Manually sorting through thousands of tweets, customer support conversations, or surveys is complex and time consuming. AI based Sentiment analysis helps businesses process huge amounts of data in an efficient and cost-effective way. Real-Time Analysis: The social media analysis can help organizations immediately identify alarming situations and they can act right away before customer churn out. Tagging text by sentiment is highly subjective, influenced by personal experiences, thoughts and beliefs. Intensifiers refer to words such as very, quite, most etc. These are the words that change sentiment of the neighboring non-neutral terms. They can be divided into two categories namely amplifiers (very, most) and down toners (slightly) that increase and decrease the intensity of sentiment, respectively. Identifying intensity of emotion may not be simple through rule based approached. Our AI based model can be enhanced further to identify intensity of emotion. R eferences R éférences R eferencias 1. Sanjiv R. Das, Mike Y. Chen, (2007) Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web. Management Science 53(9):1375-1388. 2. Walaa Medhat, Ahmed Hassan, Hoda Korashy. Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal (2014) 5, 1093-1113. 3. Fan Teng - Kai, Chang Chia-Hui. Blogger-centric contextual advertising. Expert Systems with Applications 2011; 38:1777-88. 4. Michael Hagenau, Michael Liebmann, Dirk Neumann. Automated news reading: Stock price prediction based on financial news using context- capturing features. Decision Support Systems; 2013. 5. Duric Adnan, Song Fei. Feature selection for sentiment analysis based on content and syntax models. Decision Support Systems; 2012; 53:704- 11. 6. Kaufmann JM. JMax Align: A Maximum Entropy Parallel Sentiment Analysis Tool. In proceedings of COLING’12; Demonstration papers, Mumbai 2012. Pages 277-88. 7. Chin Chen Chien, Tseng You-De. Quality evaluation of product reviews using an information quality framework. Decision Support Systems 2011; 50:755-68. 8. Apoorv Agarwal, Boyi Xie, Ilia Vovsha, Owen Rambow and Rebecca Passonneau. Sentiment Analysis of Twitter Data. Proceedings of the Workshop on Language in Social Media (LSM 2011), pages 30–38, Portland, Oregon, 23 June 2011. 9. Moraes Rodrigo, Valiati Joao Francisco, Gaviao Neto Wilson P. Document level sentiment classification: an empirical comparison between SVM and ANN. Expert Systems with Applications 2013; 40:621-33. 10. M Van de Camp, A Van den Bosch. The socialist network. Decision Support Systems, 53 (4), 761- 769, 2012. Global Journal of Computer Science and Technology Volume XXII Issue I Version I 7 ( )D © 2022 Global Journals Sentiment Polarity Identification of Social Media Content using Artificial Neural Networks Year 2022