Browsing by Author "Kumarasinghe, B"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    Analyzing the Location Feasibility for Retail Businesses using Market Location Factors
    (IEEE, 2018-12-21) Marasinghe, L; Rupasinghe, M; Kumarasinghe, B; Perera, M; Thelijjagoda, S
    The retail industry is a fast growing and a highly revenue generating industry. The location of a retail outlet is the most influencing factor for the success of the business. Therefore selecting a location for a retail store or an outlet is a challenging process. The purpose of this study is to define a method and develop a system to analyze the feasibility of a selected location for a retail store. The factors used in this method are location and market factors of a selected area. In order to define and test the method, we selected three different areas and five different retail store types. To retrieve location data, we used Google Maps web service. Consumer surveys were conducted in selected areas to get information about consumers' shopping patterns and selections. From the web service, we were able to identify transport modes, locations of competing stores and shopping areas. The findings of this study and the method described is useful in deciding the feasibility of any given location for a retail outlet. Also the specified method and model can be modified and extended to analyze different kinds of business locations.
  • Thumbnail Image
    PublicationEmbargo
    Sentiment classification of Sinhala content in social media
    (IEEE, 2020-09-24) Jayasuriya, P; Ekanayake, S; Munasinghe, R; Kumarasinghe, B; Weerasinghe, I; Thelijjagoda, S
    In this study, we focus on the classification of Sinhala social media sentiments into positive and negative classes for a particular domain (sports). We have employed machine learning algorithms and lexicon-based sentiment classification methods. We also consider a hybrid approach by constructing an ensemble classifier in which we combine Machine Learning and Lexicon based methods. For individual methods, machine learning algorithms performed best in terms of accuracy. The ensemble classifier was able to improve performance further.