Browsing by Author "Arambepola, N."

Now showing 1 - 3 of 3

Factors Influencing Mobile App User Experience: An Analysis of Education App User Reviews
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Arambepola, N.; Munasinghe, L.; Warnajith, N.
In the competitive digital world, user reviews considered as the most vital source of user feedback, provide valuable insights that reflect the success of software applications in terms of user experience (UX). As user-generated content grows exponentially, extracting meaningful information from user reviews has become an immensely challenging task. Though existing approaches can identify UX factors from mobile app reviews with a certain accuracy, prioritizing these factors poses a significant challenge. This research proposes a method to identify influential UX factors for mobile app reviews. Specifically, we did an in-depth analysis on educational app reviews of the Google Play Store. Notably, it was revealed that, although short reviews are pivotal for sentiment analysis, short reviews (word count < 3) do not significantly contribute to the generation of well-defined and meaningful topics in topic modeling. The quality of the generated topics for UX factor identification was quantitatively evaluated using coherence scores. Scores of 0.56 and 0.49 were obtained for positive and negative topics, respectively, indicating the effectiveness of the topic generation process. In addition, word embedding was utilized to prioritize the topics generated from topic modeling. There, the thumbs-up count of the reviews playsa significant role in identifying the most influencing UX factorsof educational mobile apps. The proposed method serves as a guide for researchers and practitioners to extract and prioritize UX factors from mobile app reviews in various domains.
Human in the loop design for intelligent interactive systems: A systematic review
(Faculty of Science, University of Kelaniya, Sri Lanka., 2021) Arambepola, N.; Munasinghe, L.
It is undeniable that modern computers are incredibly fast and accurate. However, computers cannot ‘think’ (act intelligently) as humans unless it is trained to learn from the past knowledge. Despite their intelligence, humans are comparatively slow in computational tasks. However, the combination of the computational capacity of computers and human intelligence could produce powerful systems beyond the imagination. This concept is called Human-in-the-Loop (HITL) where both human and machine intelligence support the creation of Machine Learning (ML) models. HITL design is an emerging technology which is used in many domains such as autonomous vehicle technology, health systems and interactive system implementations. In this research, we systematically reviewed past research of HITL systems with the objectives of identifying key benefits and limitations of the HITL design. This systematic review was conducted by analyzing 68 research papers published in top-ranked journals and conferences during the past decade. Moreover, the papers were selected using keyword-based searching and references of the most cited HITL research papers. The PRISMA model was used to exclude irrelevant papers, and keyword-based clustering was used to identify the frequent keywords in the selected papers. Although the HITL design often improves the performance of intelligent interactive systems, there are certain drawbacks of this concept when compared to fully manual or fully automated systems such as making decisions with emotional bias and being unable to take actions when demanded. Thus, we comprehensively discuss the approaches proposed by the recent researchers to overcome some of the issues of the existing HITL designs.
Impact of mobile application data usage on energy consumption
(Faculty of Graduate Studies, University of Kelaniya Sri Lanka, 2022) Arambepola, N.
Energy crisis has become a buzzword at present due to the fact that people are experiencing the first global energy crisis. On the other hand, “Affordable and Clean Energy” is one of the key sustainable development goals (SDG) proposed by the United Nation to achieve by 2030. SDG can be achieved through different approaches. As modern society is moving forward with a digital world through novel technologies, one promising way of achieving SDG is Sustainable Human-Computer Interaction (SHCI). Mobile devices are the most used digital device category by every human regardless of any demographic factor. Therefore, in the modern world, a significant amount of energy is consumed by mobile devices because people tend to establish and maintain their daily routines through mobile applications. In this research, first we systematically reviewed twenty-four (24) research papers to investigate and to analyze the mobile application usage patterns and statistics. At the initial stage, research articles were collected through mainly five (05) databases: Google Scholar, IEEE Xplore, Scopus, ACM Digital Library, and ResearchGate. Previous research studies have identified the most demanding mobile application categories by the time that research was conducted. However, the validity of those findings for today is questionable due to the rapid advancements of mobile technology over the past few years. Thus, grey literature such as statistical reports was referred to study up-to-date information as this is a rapidly updating research area. Games, Health and wellness, Grocery, Education, and E-Learning apps are found to be the most demanding mobile application categories in the world today. Moreover, data demand has been considered a proxy for energy consumption. Data demand depends on various factors such as the size of the mobile app, service provided by the app, user behavior, etc. Among them, the patterns of smartphone users are a key factor that causes the changes in the data demand. However, recent findings have shown that the behavior of smartphone usage is driven by the service and the information required for the user, not by the technology. This is a vital motivation to introduce lightweight mobile apps to address the sustainable energy issue by reducing the data demand of mobile applications that are used in daily practices. It is a common fact that mobile apps are designed for the broadest audience, and expect they work well with all users. This may indirectly consume more data and energy. For example, a heavy mobile app may have a diverse range of functionalities, but one may never use at least half of them. These applications can be redesigned in a better way to save energy and to use effectively for specific user groups.