Prabhat Kumar Mahanti

Work place: Department of Computer Science & Applied Statistics, University of New Brunswick, Canada



Research Interests: Mathematics of Computing, Analysis of Algorithms, Data Structures and Algorithms, Autonomic Computing, Software Engineering, Software Construction


Prabhat Kumar Mahanti is Professor of Dept. of Applied Statistics (CSAS), University of New Brunswick Canada. He obtained his M.Sc. from IIT-Kharagpur, India, and Ph.D. from IIT-Bombay India. His research interests include Software engineering, software metrics, reliability modelling, modelling and simulation, numerical algorithms, finite elements, mobile and soft computing, and verification of embedded software, neural computing, data analysis and multi-agent systems. He has more than 100 research papers, technical reports to his credit.

Author Articles
An Automated Real-Time System for Opinion Mining using a Hybrid Approach

By Indrajit Mukherjee Jasni M Zain Prabhat Kumar Mahanti

DOI:, Pub. Date: 8 Jul. 2016

In this paper, a novel idea is being presented to perform Opinion Mining in a very simple and efficient manner with the help of the One-Level-Tree (OLT) based approach. To recognize opinions specific for features in customer reviews having a variety of features commingled with diverse emotions. Unlike some previous ventures entirely using one-time structured or filtered data but this is solely based on unstructured data obtained in real-time from Twitter. The hybrid approach utilizes the associations defined in Dependency Parsing Grammar and fully employs Double Propagation to extract new features and related new opinions within the review. The Dictionary based approach is used to expand the Opinion Lexicon. Within the dependency parsing relations a new relation is being proposed to more effectively catch the associations between opinions and features. The three new methods are being proposed, termed as Double Positive Double Negative (DPDN), Catch-Phrase Method (CPM) & Negation Check (NC), for performing criteria specific evaluations. The OLT approach conveniently displays the relationship between the features and their opinions in an elementary fashion in the form of a graph. The proposed system achieves splendid accuracy across all domains and also performs better than the state-of-the-art systems.

[...] Read more.
Other Articles