Browsing by Author "Thelijjagoda, Samantha"

Now showing 1 - 12 of 12

Aspect-based sentiment analysis on hair care product reviews
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Kothalawala, Malki; Thelijjagoda, Samantha
Nowadays, with almost everything being shared online, people are more verbal about their consumer experiences with products via reviews. Reviews can be vital for manufacturers to get insights into consumer opinions and consumers in their purchase decisions. Sentiment analysis, referring to the extraction of subjective opinions on a particular subject within a text, is a field within Natural Language Processing, that can convert this unstructured information hidden within reviews into structured information expressing public opinion. In regards to a specific product group like hair care products, certain brands are rising in the market due to their positive public opinion on particular aspects. While ecommerce websites facilitate users to view the reviews, they do not display which reviews contain which type of opinion on which aspect at a glance. This research aims to introduce an automated process that focuses on determining the polarity of online consumer reviews on different aspects of hair care products by using Aspect-based Sentiment Analysis. The system consists of processes like data gathering, pre-processing, aspect extraction and polarity detection and follows a sequential approach to achieve the intended goal. Consequently, by deciphering the aspect-wise polarity of the reviews, the implemented system demonstrates an accuracy of 85% from the test data for overall aspects, enabling consumers to get an at a glance idea about the public opinion and manufacturers to identify their strong and weak points.
Automated Spelling Checker And Grammatical Error Detection And Correction Model for Sinhala Language
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Goonawardena, Mithma; Kulatunga, Ashini; Wickramasinghe, Raveena; Weerasekara, Thisuraka; De Silva, Hansi; Thelijjagoda, Samantha
Sinhala is a native language spoken by the Sinhalese people, the largest ethnic group in Sri Lanka. It is a morphologically rich language, which is a derivation of Pali and Sanskrit. The Sinhala language creates a diglossia situation, as the language’s written form differs from its spoken form. With this difference, the written form requires more complex rules to be followed when in use. Manually proofreading the content of Sinhala material takes up much time and labor, and it can be a tedious task. Hence, a system is necessary which can be used by different industries such as journalism and even students. At present, there are a handful of systems and research that have automated Sinhala spelling analysis and grammar analysis. In addition, the existing systems are mainly focused on either spelling analysis or grammar analysis. However, the proposed system will cover both aspects and improve upon existing work by either optimizing or re-building the process to provide accurate outputs. The proposed system consists of a suffix list built for verbs and subjects, which helps the system stand out from the current proposed solutions. This research intends to implement a service for spell checking and grammar correctness of formal context in Sinhala. The research follows a rule-based approach with some components adopting a hybrid approach. As per the literature survey, many papers were analyzed, related to different aspects of the proposed system and complete systems. The proposed system would be able to overcome most barriers faced by previous papers whilst it takes a fresh take on providing a solution.
Demystifying the concept of IoT enabled gamification in retail marketing: An exploratory study
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayasooriya, Shalini; Alles, Tharindhie; Thelijjagoda, Samantha
The retail landscape is evolving rapidly as firms embrace innovative technologies in an attempt to stay ahead of the aggressive competition prevalent within the industry. Gamification is one such innovative technology that has been gaining popularity in recent times. This study aims to explore the application of Gamification in the context of Retail Marketing in Sri Lanka and ultimately propose a concept for a Gamified application that can be used by customers of moderntrade retailers. The study took an exploratory qualitative approach where intensive surveys of literature and in-depth interviews with a judgmental purposive sample of seven marketing professionals in the modern-trade retail industry were conducted to determine the current play of technology in retail marketing as well as the drivers & challenges of Gamification adoption. Further, in-depth interviews with the customers of such organizations were conducted in gathering user preferences and design recommendations for a Gamified app. Thematic analysis was carried out in deriving insights. Findings show that the retail firms currently employ several technologies in line with those discussed in existing literature such as loyalty card systems, digital signage, VR technologies, online Gamification amidst others in carrying out their marketing efforts. Gamification is predominantly applied in the online context as opposed to the offline (in-store) context. Furthermore, the key drivers that propel firms to implement novel technology like Gamification are to generate customer insights, enhance customer experience and achieve marketing related KPI targets. Conversely, inadequate technology infrastructure, justifying the focus on a niche crowd of techoriented customers and slow ROI pose as challenges in the process of Gamification adoption. Three main themes emerged upon exploring user preferences and design recommendations for a Gamified app and are identified as information at the touch of a fingerprint, automation & integration and use of game mechanics. Ultimately by incorporating these insights gathered, a concept for a Gamified app was proposed.
Designing of a Voice-Based Programming IDE for Source Code Generation: A Machine Learning Approach
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Nizzad, A.R. M.; Thelijjagoda, Samantha
Humans are precise in recognizing natural languages and responding contextually unlike machines. However, speech recognition or Automatic speech recognition often refers to converting human speech or voice to textual information with the help of artificial intelligence algorithms. With the advancement of Artificial Intelligence technologies and extensive research being conducted in AI, speech recognition has received much attention and has emerged as a subset of Natural Language Processing where the advancement and accuracy in speech recognition will open many ways to provide a high standard of human-computer interaction. In this study, using the pre-trained transformer model with a transfer learning approach, the English to Python dataset was used to train the transformer model to produce syntactically correct source code in python. Additionally, the Word2Vec model was used to generate voice-to-text as input for the model. For the purpose of demonstration, a custom Python IDE is developed to generate source code from voice input. The results and findings suggest that in the transformer model, with the use of transfer learning, any dataset can be trained to produce syntactically correct source code. The model’s training loss and validation loss were below 5 and 2.1, respectively. Future research can focus on generating valid source code from any human spoken language without restricting it to English only.
Detecting human emotions on Facebook comments
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Chathumali, E.J.A.P.C.; Thelijjagoda, Samantha
Human emotion detection plays a vital role in interpersonal relationships. From the early eras, automatic recognition of emotions has been an active research topic. Today, sharing emotions on social media is one of the most popular activities among internet users. However, when it comes to a specific domain like emotion detection in social media, it is still on a research-level. There are less number of applications have been developed to detect emotions online, using online comments and user comments. The aim of this research is to develop a system that identifies human emotions on Facebook comments. Among the different social media platforms, this research specifically focuses on Facebook comments written in the English language to narrow down the problem. The research is based on Semantic analysis, which comes under Natural Language Processing (NLP) and the system development consists of four major steps, including the extraction of Facebook comments via Graph API, preprocessing, classification and emotion detection. To classify the emotions, a classification model was created by using Naïve Bayes Algorithm. When it comes to marketing, emotions are what lead your onlookers to purchase. By using the detected emotions, marketers can promote their campaigns by changing online advertisements dynamically. The results obtained through testing the system show that it is capable of accurately identifying human emotions hidden in Facebook comments with an accuracy level of 80%, making it highly useful for marketing purposes.
Healbot: NLP-based Health Care Assistant for Global Pandemics
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Anushka, Shan; Thelijjagoda, Samantha
Since it was detected, coronavirus (also known as COVID-19) has become a worldwide epidemic. The surge in patients has made it challenging for hospitals and medical professionals to keep up due to the increasing number of recorded incidents. When the pandemic starts, it is getting really hard to visit a medical specialist, even in more remote areas. According to the Johns Hopkins university’s Covid dashboard, approximately 220 million Covid cases were reported worldwide [2]. According to government hospital reports, 666,086 cases were found in Sri Lanka [3]. It’s a massive amount to handle for the health sector and the country. Consequently, there are many deaths reported every day as a result of the challenges in inpatient care. Because all patients are treated in their homes, this must be done efficiently. Only the most urgent cases are being treated in hospitals. Hospitals and quarantine centers are overcrowded. People in remote areas are also trying to treat the disease without knowing anything about it because they have limited access to information. This is because it needs a Chatbot to help with diagnosing Covid symptoms at home, and to assist patients in finding the right treatment options. An artificial intelligence (AI) Chatbot has been developed with the goal of diagnosing COVID-19 exposure and advising rapid remedies. As part of this analysis, relevant past research was reviewed to establish the best reliable approach for predicting COVID-19 in people. There was an integration of Logistic Regression, Decision Trees, and Random Forests to develop the model. The model was trained with the clinical data taken from the COVID-19 patients and machine learning models are evaluated to see how accurate they are. It was determined how accurate the algorithms were. The patients who were infected with COVID-19 were examined by using implemented prototype to predict the severity level and the trained model makes use of RASA Framework, FastAPI, and MongoDB for the purpose of making predictions. The accuracy of the trained model and random sample tests seems similar. So, the prototype’s efficacy is perfectly matched. In rural areas, it can help patients by providing them with proper advice on how to treat, what preventive measures are, and what nearby health services are. It can also help patients by reducing the psychological damage that may be caused by their isolation from other people.
Machine translation system to convert Sinhala and English Braille documents into voice
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Anuradha, K. Sasindu; Thelijjagoda, Samantha
Reading Braille documents are a time-consuming and labor-intensive task. A blind person should touch every Braille letter by his or her fingers. Therefore, high sensitivity in fingers and memorizing every Braille letters are key factors in Braille reading. Due to enhancement in technology, several Optical Character Recognition (OCR) systems have been introduced for different languages in different parts of the world. However, in Sri Lanka, there are no systems that extract Sinhala or English Braille characters using OCR and convert those Braille codes to sound output. The main purpose of the research is to create a system that extracts both Sinhala and English Braille segments from a given Braille document and makes the Braille content into voice. At the beginning Embossed Sinhala or English Braille image which took from webcam or a highresolution phone will use for image processing techniques such as gray scaling, thresholding, erosion, and dilation. Erosion and gray scaling help to eliminate the noise and the noise-free image used to detect contour. After pre-processing, the image using an OpenCV library do the segmentation and character extraction. Braille character recognition has done by taking binary to decimal equivalent numbers. Before generating voice output, recognized Braille letters should convert to corresponding language letters (either Sinhala letter or English) and mapping English letters can directly generate English words but in Sinhala need an additional step called Unicode Mapping to generate a Sinhala word. When a Braille document is in high quality, the system will reach for 95 percent accuracy level and generally, results have around 85.30 percent success rate. This software provides many usability characteristics to increase simplicity when it’s using OpenCV and related technologies. Even teachers can use this to improve their teaching terminologies and explain things more clearly in their lessons.
A Model to Manifest the Inadequacy of Awareness in Cyber Bullying among Adolescents and to Accent its Dire Need
(Department of Marketing Management, Faculty of Commerce and Management Studies, University of Kelaniya, Sri Lanka., 2021) Liyanage, Chamodi; Athauda, Kaushaka; Inali, Hesha; Silva, Rochana; Dunuwila, Vandhana; Thelijjagoda, Samantha
Cyber bullying can be identified as the use of electronic communication to bully a person, typically by sending message intimidating or threatening nature. As a result of the anonymity that the internet may offer, cyberbullying varies from standard bullying. There are some of forms that the cyber bullies use such as harassment, denigration, impersonation, outing, trickery, exclusion, cyberstalking, and cyber threats. cyber bullying could be threating to a one's life in different ways. Being a victim of cyber bullying could result on empathy, anger, suicidal thoughts are some of the factors that could harm a person life. The main concern that surfaced when addressing this issue is that in Sri Lanka this subject does not exist as an issue in the eyes of public that needs addressing. The mere existence of this dilemma is in the shadows as it is generally accepted by society. The main objective of the study is to introduce a model that can be used to bring awareness on misuse of social media among adolescents. It attempts to understand the effect of technological illiteracy, psychology of the users and the activeness of the legal framework on the crisis of cyber bullying among the adolescents in Sri Lanka. The study was conducted with qualitative techniques to achieve the objectives of the study. The data were collected through both primary and secondary sources. The primary sources included an open-ended questionnaire and an in-depth interview while the secondary sources were based on reading past literature done by previous researchers. Collectively there were 384 participants for the questionnaire representing all the adolescents in the country within the age group of 12-22. Total of 10 in-depth interviews were conducted with volunteered adolescents and 3 specific interviews with industry experts from CERT, CID, and Child protection authority. The data collected were analyzed using grounded theory and thematic analysis. The results of the study can be summarized with a total count of 384 responses in the questionnaire. The responders have mentioned that they are mostly familiar with Facebook, Instagram and YouTube as the social media platforms and majority are using these platforms daily and hourly. 60% of the responders were unaware about the term cyber bullying but when they were inquired about the experiences they have gone through, they were exposed to cyber bullying. The majority responded that they have witnessed or gone through trolling which is one phase of cyber bullying. Also, when the activeness of legal factor on this crucial factor is concerned, the realization of high need of legal coverage was visible. The study was concluded with a model that is introduced to bring the necessary awareness among the adolescents by giving them proper technological literacy and understanding on the proper ways to use social media and internet and to minimize the debacle occurring continuously among the users.
A modified cognitive complexity metric to improve the readability of object-oriented software
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayalath, Thilini; Thelijjagoda, Samantha
Complexity of software can be identified as a term which expresses the difficulty level of reading, understanding, maintaining and modifying the software. This helps to the quality improvement of the software and maintenance process of the software through a long time period without any obstacle. Therefore, software complexity metrics have been introduced to calculate the complexity of a software using numerical values. While there are number of metrics which calculate the complexity of object-oriented programs, they only consider one or two object-oriented concepts. As a result of that, there is no single metric which has the capability of measuring the complexity of a program based on multiple object-oriented concepts. This research aims to build a new metric to evaluate the complexity of an object-oriented program in order to improve the readability. The new metric has been built based on the influence of previous objectoriented metrics and some disregarded factors in calculating the complexity. In order to evaluate the new metric, Weyuker’s properties and Briand’s properties are used. The new metric acquires most of the object- oriented concepts in calculating the complexity and helps to improve the readability of the software as well. In fact, it makes it easy to handle the maintainability, reusability, portability and reliability of the software, when readability is high. This will result in increasing the overall software quality.
A modified cognitive complexity metric to improve the readability of object-oriented software
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayalath, Thilini; Thelijjagoda, Samantha
Complexity of software can be identified as a term which expresses the difficulty level of reading, understanding, maintaining and modifying the software. This helps to the quality improvement of the software and maintenance process of the software through a long time period without any obstacle. Therefore, software complexity metrics have been introduced to calculate the complexity of a software using numerical values. While there are number of metrics which calculate the complexity of object-oriented programs, they only consider one or two object-oriented concepts. As a result of that, there is no single metric which has the capability of measuring the complexity of a program based on multiple object-oriented concepts. This research aims to build a new metric to evaluate the complexity of an object-oriented program in order to improve the readability. The new metric has been built based on the influence of previous objectoriented metrics and some disregarded factors in calculating the complexity. In order to evaluate the new metric, Weyuker’s properties and Briand’s properties are used. The new metric acquires most of the object- oriented concepts in calculating the complexity and helps to improve the readability of the software as well. In fact, it makes it easy to handle the maintainability, reusability, portability and reliability of the software, when readability is high. This will result in increasing the overall software quality.
Sentiment classification of Sinhala content in social media
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayasuriya, Pradeep; Ekanayake, Sarith; Munasinghe, Ranjiva; Kumarasinghe, Bihara; Weerasinghe, Isuru; Thelijjagoda, Samantha
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.
A solution to overcome speech disorder of patients using Brain Neuron EEG Signals
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayawickrama, J.A.D.T.; Thelijjagoda, Samantha
Speech disorders are neurodevelopmental disorders such as Stuttering, Dysarthria, Dysphonia and Aphasia associated with left inferior frontal structural anomalies that involve repeating or prolonging a word, syllable or phrase, or stopping during speech and making no sound for certain syllables. Most of the people who are suffering from speech disorders encounter difficulties in professional communication. Since people are busy with their day to day life, it is not practical to spend more time in consulting a doctor or do speech therapies for their medical issues. The speech therapist generally charges a significantly much higher rate for a single speech therapy practice, which the patient needs to practice at least twice or more for a week to get a better result. In an economy like Sri Lanka, people with average income cannot afford such an amount of money. Therefore, an innovative desktop application for speech disorder patients to overcome this problem has arisen. The main aim of this application is to reduce the speech imperative percentage of speech disorder patients via capturing the electroencephalogram feed of speech motor (Broca's area) using brain neuron O1, O2, C3, C4, F3, F4, F7, F8 electrodes and analyzing it to identify speech imperative issues. This system identifies the current impact on the left hemisphere of the brain (Broca’s area) using EEG neurofeedback. Using speech voice analysis, the system provides the user to measure the articulation interference of the speech process. Self-Learning video tutorials are available for the clinical practices and treatments are available as prolong, relaxing, and humming exercises. Patients can track down the improvements daily or monthly by the rating system which makes the system unique among all other systems and the result can be directly sent to the desired consultant/neurophysiologist by the system itself. Patients can save time and the total cost of a therapy fee by using this system.