Sentiment Analysis of Customers
This work is licensed under a Creative Commons Attribution 4.0 International License.
The copyright to this article is transferred to the University of Public Service Budapest, Hungary (for U.S. government employees: to the extent transferable) effective if and when the article is accepted for publication. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The author warrants that this contribution is original and that he/she has full power to make this grant. The author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors.
An author may make an article published by University of Public Service available on a personal home page provided the source of the published article is cited and University of Public Service is mentioned as copyright holder
Abstract
There is an economic and political need to learn and know more and more information about customers, and the social media has recently become the most powerful tool for interaction with people. Customers became users in the social media, who express their opinion and share it with not only companies but also other users. Since a huge amount of reviews, opinions and comments appeared, there is a necessity to extract, aggregate, and analyse them; these are the aims of sentiment analysis. In this paper the technological details of sentiment analysis are presented. The problem types and their solution with text mining are described. Text mining is based on data mining, but steps of text preprocessing with tokenisation, stemming, filtering is an additional important phase before the data mining procedure. The correctness of sentiment analysis solutions can be measured by different validation methods. At the end of the paper the final conclusion is presented.