Quantifying Inference Learning Model to Explore Twitter User Emotions
G.Srinivasa Raju1, M.Ajay Dilip Kumar2, S.Suryanarayana Raju3
1G.Srinivasa Raju, C.S.E, S.R.K.R. Engineering College, Bhimavaram, India.
2M.Ajay Dilip Kumar, C.S.E, S.R.K.R. Engineering College, Bhimavaram, India.
3S.Suryanarayana RAJU, C.S.E, S.R.K.R. Engineering College, Bhimavaram, India.
Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 1906-1910 | Volume-8 Issue-10, August 2019 | Retrieval Number: J92530881019/2019©BEIESP | DOI: 10.35940/ijitee.J9253.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Increasing social media used by different peoples express their opinions and feelings in the form sentences and text messages. So that extracting the information from message i.e which consists different issues in text and identifying anxiety depression of individuals and measuring well-being or mood of a community. This is because of its significance in a wide scope of fields, for example, business and governmental issues. Individuals express assessments about explicit themes or elements with various qualities and powers, where these estimations are firmly identified with their own sentiments and feelings. Various techniques and lexical assets have been proposed to break down feeling from normal language writings, tending to various assessment measurements. In this article, we propose a novel inference methodology for quantifying and inferring the Twitters users’ conclusion grouping utilizing distinctive notion measurements as meta-level highlights. We consolidate angles, for example, assessment quality, feeling and extremity markers, created by existing estimation investigation strategies and assets. Our exploration demonstrates that the mix of assumption measurements gives critical improvement in Twitter feeling characterization errands, for example, extremity and subjectivity
Keywords: Twitter, Information extraction, social media, machine learning, assessment, sentiment analysis.
Scope of the Article: Smart Learning and Innovative Education Systems