Abstract:
With emerging technologies and constantly changing lifestyles, shopping has become
an essential factor in society. There are people who frequently do shopping as a major
activity in their day-to-day life. They tend to use the internet to find the best sellers.
People often browse through many reviews to arrive at an informed decision. As a
solution, we propose a community-based software platform that analyses customer
reviews to provide tailored recommendations. In the proposed solution, textual
feedback is analyzed using sentiment analysis, which helps to categorize user
responses. An important factor is proposed system can analyze Sinhala and English
textual feedback. The analyzed data is then stored as negative, positive, or neutral
feedback. We found that customers mainly consider four features when they are
selecting a seller, the price of the goods, the quality of the goods, customer service,
and after-sales services of the seller. A score for each feature and an overall score is
calculated based on the feedback to rank the sellers. The overall score is calculated
using a weight-allocating mechanism which increases the accuracy of the results. The
system acts as a common software platform that helps to improve their shopping and
selling experiences.