Addressing Sentiment Analysis Challenges within AI Media Platform: The Enabling Role of an AI Powered Chatbot

Avram Constantin and Rusu Robert
Additional contact information
Avram Constantin: Dunarea de Jos University of Galati, Romania
Rusu Robert: Dunarea de Jos University of Galati, Romania

Risk in Contemporary Economy, 2021, 399-406

Abstract: This paper seeks to classify text with a supervised machine learning algorithm, embedded into an AI powered chatbot. A data set containing tagged texts is used to classify text from IMDb movie review data set, Reviews for Sentiment Analysis - Amazon and Earphones Reviews. The goal is to automatically classify texts into one or more predefined categories. Using supervised learning methods, we developed a model that will use the labelled data set as input. These texts are classified according to syntactic or linguistic characteristics. Research findings outlined that the choice of characteristics for the classification of the sentiments is relevant for leveraging the best possible accuracy, considering Lexicon sentiment, Rules for opinions, Emoticons, Frequency and presence of terms.

Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.rce.feaa.ugal.ro/images/stories/RCE2021/AvramRusu.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ddj:fserec:y:2021:p:399-406

Access Statistics for this article

More articles in Risk in Contemporary Economy from "Dunarea de Jos" University of Galati, Faculty of Economics and Business Administration Contact information at EDIRC.
Bibliographic data for series maintained by Gianina Mihai ().