Browsing by Author "Asanka, Dinesh"

Now showing 1 - 4 of 4

Aspect Based Multi-Class Sentiment Dataset for Bilingual eWOM of Commercial Food Products
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Edirisuriya, Binguni; Asanka, Dinesh; Wijayanayake, Janaka
Aspect-Based Sentiment Analysis for product review opinion analysis is commonly utilized by the commercial food products manufacturing businesses to drive decisions regarding products. However, the general consumers are not facilitated with decision making ready end-user applications which generates insights to arrive at the purchase decision at the time of purchase due to the unavailability of products’ attribute-wise analysis-ready data. Although Electronic Word of Mouth (eWOM) platforms are comprised of opinions with a diversity of languages and expression formats, themselves do not generate any value to make comparable decision making. Hence, there is an existing gap of impactful information retrieval by the consumer to aid the purchase. Therefore, creating a publicly available analysis-ready dataset for the commercial food product domain contributes significantly to the Sri Lankan consumers and Government organizations. Through our research work, a manually annotated bilingual eWOM opinion text dataset for selected commercial food products categories has been delivered in which the opinions expressed in the Sinhala language have been translated into English language and each opinion has been manually rated into five levels by two domain experts. Two product attributes, “Price of the product”, “Safeness of product” have been considered as aspects to conduct the Aspect-Based Sentiment Analysis. This study describes the sub-tasks performed to conduct the Aspect- Based Sentiment Analysis on the dataset along with the basic statistical evaluation of the dataset. We have presented results on the performance of the dataset by utilizing an existing Long Short-Term Memory Model.
Defaulter Prediction in the Fixed-line Telecommunication Sector Using Machine Learning
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Ginige, Sachini; Rajapakse, Chathura; Asanka, Dinesh; Mahanama, Thilini
In the modern connected era, the telecommunications sector plays a critical role in enabling efficient business operations across all industries. However, defaulting customers who fail to pay their dues after consuming services remain a significant challenge in the industry. Defaulters pose a risk to service providers, calling for measures to lessen both the probability of occurrence as well as its impact. Early identification of defaulters through prediction is a possible solution that enables proactive measures to mitigate the risk. However, the nature of the fixed-line product segment poses additional constraints in identifying defaulters, highlighting an existing knowledge gap. The research aims to evaluate the effectiveness of machine learning as a technique for the prediction of defaulters in the fixed-line telecommunication sector, and to develop an effective predictive model for the purpose. The success of machine learning techniques in analysis and prediction over traditional methods prompted its use in this study. The study followed the design science research methodology. An analysis was conducted based on past transaction data. Special consideration was given to the scenario of customers with little to no transaction history. Based on the analysis, a feature list for identifying defaulters was compiled, and multiple predictive models were developed and evaluated in comparison. The resulting predictive model, which uses the Random Forest technique, shows high performance in all considered aspects. The findings of the study demonstrate that machine learning techniques can effectively predict defaulters in the fixed-line telecommunication sector, with significant implications for mitigating the risk associated.
Recommendations to Increase the Customer Interaction of E-commerce Applications with Web Usage Mining
(Institute of Electrical and Electronics Engineers (IEEE), 2023) Rajapaksha, Pamuditha; Asanka, Dinesh
Web mining uses data mining methods to extract knowledge from web applications. It is used in e-commerce to track client browsing behavior. The issue with e-commerce is that we only know about our customers once they place an order. The primary goal of this endeavor is to identify a viable option to continue operating a profitable online store by better understanding customers. The research project aims to identify customer preferences and purchase behaviors so that improvements can be made to e-commerce platforms based on these findings. Web usage mining enables the seller to monitor, investigate, and identify patterns from compiled data to create a fundamental statistical foundation for decision-making. To properly use web usage mining, it is necessary to collect qualitative visitor data, which enables researchers to determine whether a visitor has viewed a product repeatedly, added it to their wishlist before making a purchase, or bought it during a particular season, etc. A limited number of publications were found in this domain, and most of the work was done with limited data like user clicks, navigation paths, etc. In this research, event listeners have been added to the e-commerce application to capture user actions and behavior towards a specific product on the application. Four classification algorithms experimented with the event data and identified the most effective algorithm to develop the prediction model. Users' purchasing patterns and buying behaviors were analyzed and identified using the model developed with the Random Forest classification algorithm. Recommendations for the e-commerce applications were developed according to the identified user behavior and purchasing patterns. This strategy will lead the ecommerce industry to a profitable economic point by increasing the effectiveness of the application.
Sentiment Reason Mining Framework for Analyzing Twitter Discourse on Critical Issues in US Healthcare Industry
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Edirisinghe, Rasika; Asanka, Dinesh
This research study employs machine learning and textual analysis techniques to examine the US healthcare system through the analysis of Twitter data. By leveraging domain-specific keywords and hashtags, a customized data collection algorithm is utilized to gather a substantial dataset of tweets related to #medicaid and Medicaid. The collected tweets undergo a comprehensive analysis using sentiment analysis, sentiment spike detection, keyword extraction, k-means clustering, topic modeling, and textual association. The study aims to extract insights and identify critical issues hindering access to quality healthcare. The findings have implications for marketing strategies, enabling companies to better align their offerings with customer needs. Additionally, policymakers and healthcare organizations can benefit from the insights gathered, gaining valuable knowledge about the public's concerns, preferences, and satisfaction with US healthcare services and systems. By employing machine learning and textual analysis techniques, this research contributes to a deeper understanding of public sentiment and provides data-driven insights to address challenges in the healthcare domain.