Iterative Framework on Upgrading Lexicons for Sentiment Analysis

Andreeski, Cvetko (2016) Iterative Framework on Upgrading Lexicons for Sentiment Analysis. In: ETAI2016, 22-24 Sep 2016, Hotel Drim - Struga.

Full text not available from this repository. (Request a copy)


In many different areas of working, processing client reviews is very important part of the feedback, and helpful tool for improving the products and services. This subject of research is present in many papers about text and sentiment analysis. In many cases the dictionary or domain specific lexicons are important part of the accuracy of analysis. In this paper we propose the iterative framework for upgrading the lexicons and testing the accuracy on selected corpus of documents. The system takes into account the segments of the sentences, presents the imperfections of the lexicon and can lead the user to better domain-specific dictionary. Results and some simulation are given in the paper, and they are compared with the results given by standard classification software for the same testing corpus.
Keywords: sentiment, Naïve Bayes, iterative, analysis

Item Type: Conference or Workshop Item (Paper)
Subjects: Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions: Faculty of Tourism and Hospitality
Depositing User: Mr Bojan Sekulovski
Date Deposited: 12 Oct 2017 10:42
Last Modified: 13 May 2019 09:37

Actions (login required)

View Item View Item