http://dlib.iit.ac.lk/xmlui/handle/123456789/284 Wed, 22 Apr 2026 13:09:44 GMT 2026-04-22T13:09:44Z http://dlib.iit.ac.lk/xmlui/handle/123456789/469 “Falso” A fake review identification system for online products using supervised learning methods Jayawardena, Nethmi Venu H M Online shopping is the act of purchasing products or services through the internet. When shopping online, product reviews are one of the only methods of helping a buyer with their purchase decisions. Since many online sellers exist, the competition among them has led to the rise of fake online reviews to manipulate buyer purchase decisions. This is known as fake review spamming. By fake review spamming sellers can boost their own ratings to improve sales or degrade a competing seller’s ratings to reduce their sales. Fake review spamming is a rising problem and many previous researchers have attempted to solve this problem using methods such as opinion mining, optimization algorithms and machine learning. This research proposes a natural language processing and machine learning based approach to identify fake review spamming. Natural language processing is used for pre-processing textual inputs and extracting its features. Machine learning classifiers use these extracted features for identifying fake reviews. By comparing five supervised classification algorithms, it was possible to achieve a detection accuracy of 81% with a gradient boosting classifier called XGBoost. Using this classification approach, a fake review identification system for online products was developed under the name ‘Falso’. This solution was designed to be used by the administrators of an online shopping application. It allows an administrator to view the authenticity of a single review or an entire dataset of reviews at once. Using Falso, the administrators will be able to control fake review spamming to make sure that buyers will not be tricked into incorrect purchase decisions. Tue, 01 Jan 2019 00:00:00 GMT http://dlib.iit.ac.lk/xmlui/handle/123456789/469 2019-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/468 “TaxiMate” Taxi Demand Prediction using Time Series Forecasting Hassim, Thilan Rukshan Taxis are one of the most famous modes of public transportation since the 17th century. With the rapid development of technology and lifestyle, the demand for taxi services has only grown higher over the years. To ensure efficient functionality and profitability, it is important for taxi drivers to have a basic understanding about the future taxi demand in different cities. Usually this understanding is achieved with experience, but it is time consuming and not a very reliable process. The absence of methods to identify this is a large problem in this domain. Previous researchers have attempted to use different approaches such as long short-term memory, gradient boosting techniques and autoregressive moving average models to predict the future demand for taxis. This study proposes a solution for this problem by predicting the future taxi demand of a city using a new forecasting algorithm known as Facebook Prophet. Taxi demand has a high variance and many independent variables such as weather, holidays and time of the day have a direct impact on its value. These variables in combination with historic taxi data was used to calculate the future taxi demand using Prophet. Results showed that Prophet was able to provide the fastest output with the lowest error percentage from the tested algorithms ARIMA, SARIMA and VAR. Based on these results, the TaxiMate web application was developed to allow taxi drivers to input a date and a location to identify the future taxi demand with ease. Tue, 01 Jan 2019 00:00:00 GMT http://dlib.iit.ac.lk/xmlui/handle/123456789/468 2019-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/467 A Dynamic World Generation System Based on Player Decision & Storyline Singhe, Manul R. This research addresses the problem of single player games having low replay value. An in-depth analysis and review of the problem is discussed. This system suggest the possible method of overcoming this problem by combing already existing technologies and techniques to add high replay value to single player games by trying to eradicate the problem. By utilizing procedural generation and AI to work in real-time, the research propose the solution of developing a system that generates the game environment, inclusive of non-player characters, collectables, pick-ups and other game related content to be generated based on the player character’s attributes and the game state. The literature reviews shows in depth the literature that was used and the knowledge gained from them to be incorporated in development of this system. The testing and evaluation shows what was achieved through this project and the implementation discusses in-depth how it was achieved Tue, 01 Jan 2019 00:00:00 GMT http://dlib.iit.ac.lk/xmlui/handle/123456789/467 2019-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/466 An Algorithmic Approach to Find the Optimal Transportation Method in Sri Lanka Abeysuriya, Buwendra There are multiple methods of ground transportation available for people. Trains, cable carts, Buses, E-hailing applications, and many more. All these services help the users to travel from one place to another. But because most countries have more than 3 types of transportation services available for the user it will be a bit of a challenge to find the best combination of rides or ride to get the user to the destination faster or cheaper. The purpose of this document is to find existing solutions to this problem and review them. Before we start reviewing the below paragraphs will give a more in-depth explanation of what the problem is.E-hailing Applications was one of these innovations that made people's lives much easier. This application allowed the users to order transport services using the user's smartphone and allows anyone who has a vehicle to become a driver and make some extra cash while going home. “Travis Kalanick says Uber has 40 million monthly active riders” (Travis Kalanick 2016). The application is available worldwide. that said today there are more than 100 plus E-hailing applications out there. All competing to become the best in their respective countries. As such Sri Lanka also has around 10 E-hailing Applications. There are lots of ground public transportation services given to the citizens by their country’s government. Some of this service are buses, trains and simpler services. Most public services have a pick-up and a drop off location. Because of this, the user won’t be able to specify a location to get off at but in return, this service is much cheaper and sometimes faster. Because of this, the user can combine this service to get to a specific location much faster. For example, since trains are faster than buses the user can plan to take a bus to the train station and catch a train to the nearest station to the destination. This is precisely the matter what the solution promoted this document will help the user do. The application will plan the rides for you and display the most optimal combination of transportation method. This research is conducted to explore the perception of selecting optimum transportation of Sri Lanka. Most countries that have lots of methods of transportation like the UK they have applications to support the users to find the optimum way of transportation. The optimum way of transportation is the fastest and cheapest way for a person to get from one location to another, using all or some of the available transportation methods. Tue, 01 Jan 2019 00:00:00 GMT http://dlib.iit.ac.lk/xmlui/handle/123456789/466 2019-01-01T00:00:00Z