Knowledge Discovery From Vernacular Expressions: An Application of Social Media and Sentiment Mining

Knowledge Discovery From Vernacular Expressions: An Application of Social Media and Sentiment Mining

Nishikant Bele (International Institute of Health Management Research, New Delhi, India), Prabin Kumar Panigrahi (Department of Information Systems, Indian Institute of Management Indore, Indore, India) and Shashi Kant Srivastava (Department of Information Systems, Indian Institute of Management Indore, Indore, India)
Copyright: © 2018 |Pages: 18
DOI: 10.4018/IJKM.2018010101

Abstract

This article describes how knowledge discovery is a frontier research issue of knowledge management, and social media provides an opportunity for knowledge discovery that was at no other time as virtuous as the present. Despite the fact that, the articulations in national dialects via web-based networking media is mounting day by day. This discovery endeavor in regional languages is rare. The usage of Hindi, the Indian National language, is also observing the similar trend. Any expression in social media contains multiple features. Discovering the hidden sentiments behind these features have wider functions. This article is the first attempt to mine the opinion at the features level in the Hindi language. The principle contribution of this article is the development of context specific corpus in the Hindi language. Based on this corpus authors extract the sentiments on one of the prominent leader of India at the feature level. Opinion mining conclusion based on present work is reproduced likewise in the subsequent election results.
Article Preview
Top

1. Introduction

Knowledge is the key asset of an organization (Gloet & Samson, 2016). In order to safeguard their interests and survive in the face of multidimensional pressure, organizations are showing keen interest in knowledge management (KM) (Carvalho & Gomes, 2017; Ryan, Zhang, Prybutok, & Sharp, 2012; Twum-Darko & Harker, 2017; Yesil & Hirlak, 2013). Knowledge discovery (KD) is the foremost component of KM (Smolnik, Kremer, & Kolbe, 2005) and includes information mapping, knowledge collaboration, disseminate learning, business insight, and knowledge security (Gold et al., 2001; Grant, 1996).

Scholarly writing is the primary source of KD. The English language overshadows the academic work of the world (Cavazos, 2016; Choi, 2010; Leppänen & Pahta, 2012) and it has been found that KD in native languages is almost disregarded. Text mining and sentiment mining are key components of KD for various organizations (Handzic, Lagumdzija, & Celjo, 2008) however, text mining and sentiment mining literature is also dominated by the English language (Harrag, 2014; Korayem, Aljadda, & Crandall, 2016; Vijayarani, Ilamathi, & Nithya, 2015).

Research points to a growing need to mine knowledge in native languages to gain contextual business insights. The aim of this study is to highlight the role of Hindi language in contextual knowledge discovery and to develop a framework to uncover sentiments from a large pool of textual data.

The rest of this paper is organized as follows: Section 2 comprises of literature review while Section 3 showcases the methodology used and our purposed framework. Section 4 describes the analysis and results of the study, and Section 5 discusses the implications, limitations, and future direction of research.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 16: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing