Browsing by Author "Nyamawe, Ally S."
Now showing 1 - 17 of 17
Results Per Page
Sort Options
Item A deep feature interaction and fusion model for fake review detection: Advocating heterogeneous graph convolutional network(Elsevier BV, 2024) Duma, Ramadhani Ally; Niu, Zhendong; Nyamawe, Ally S.; Manjotho, Ali AsgharIn contemporary real-world scenarios, opinion spammers are hired to fabricate reviews that unfairly promote or demote particular products or services for personal gain. Although considerable attention has been devoted to addressing the problem, existing approaches often overlook the heterogeneous nature of reviewer–product interactions. Specifically, the correlation between review text (comments) and overall ratings, which provides various latent rich information to expose fake reviews, remains inadequately explored. Current methodologies focus on limited interactions, such as reviewer–review, product–review, or reviewer–product interactions, while neglecting significant aspects like reviewer–review–product and reviewer–rating–product interactions, leading to inadequate classifier performance. Motivated by this observation, this study proposes a novel Deep Feature Interaction and Fusion Model (DFIFM) whose ideas are five-folds: (a) constructing a reviewer–product interaction bipartite graph that represents heterogeneous feature node interactions through review text and overall rating values; (b) recognizing the existing mutual interactive relationship between review text and overall rating features, we construct a unified GCN to gain additional insights into feature relationships and capture mutual heterogeneous interactions between nodes; (c) to handle the encoding of unstructured review text features as edge attributes, we adopt a convolutional neural network (CNN); (d) attention mechanisms and fusion techniques are employed to capture interdependencies among reviewer–product latent features; and (e) a Multilayer Perceptron (MLP) utilizes the resulting latent feature representation for review classification. Experimental results on three publicly available datasets demonstrate its superiority over state-of-the-art baselines.Item Automated recommendation of software refactorings based on feature requests(Institute of Electrical and Electronics Engineers ( IEEE), 2019) Nyamawe, Ally S.; Liu, Hui; Niu, Nan; Umer, Qasim; Niu, ZhendongDuring software evolution, developers often receive new requirements expressed as feature requests. To implement the requested features, developers have to perform necessary modifications (refactorings) to prepare for new adaptation that accommodates the new requirements. Software refactoring is a well-known technique that has been extensively used to improve software quality such as maintainability and extensibility. However, it is often challenging to determine which kind of refactorings should be applied. Consequently, several approaches based on various heuristics have been proposed to recommend refactorings. However, there is still lack of automated support to recommend refactorings given a feature request. To this end, in this paper, we propose a novel approach that recommends refactorings based on the history of the previously requested features and applied refactorings. First, we exploit the stateof-the-art refactoring detection tools to identify the previous refactorings applied to implement the past feature requests. Second, we train a machine classifier with the history data of the feature requests and refactorings applied on the commits that implemented the corresponding feature requests. The machine classifier is then used to predict refactorings for new feature requests. We evaluate the proposed approach on the dataset of 43 open source Java projects and the results suggest that the proposed approach can accurately recommend refactorings (average precision 73%).Item Automated recommendation of software refactorings based on feature requests(IEEE, 2019) Nyamawe, Ally S.; Liu, Hui; Niu, Nan; Umer, Qasim; Niu, ZhendongDuring software evolution, developers often receive new requirements expressed as feature requests. To implement the requested features, developers have to perform necessary modifications (refactorings) to prepare for new adaptation that accommodates the new requirements. Software refactoring is a well-known technique that has been extensively used to improve software quality such as maintainability and extensibility. However, it is often challenging to determine which kind of refactorings should be applied. Consequently, several approaches based on various heuristics have been proposed to recommend refactorings. However, there is still lack of automated support to recommend refactorings given a feature request. To this end, in this paper, we propose a novel approach that recommends refactorings based on the history of the previously requested features and applied refactorings. First, we exploit the state of-the-art refactoring detection tools to identify the previous refactorings applied to implement the past feature requests. Second, we train a machine classifier with the history data of the feature requests and refactorings applied on the commits that implemented the corresponding feature requests. The machine classifier is then used to predict refactorings for new feature requests. We evaluate the proposed approach on the dataset of 43 open source Java projects and the results suggest that the proposed approach can accurately recommend refactorings (average precision 73%).Item Citation Classification Using Multitask Convolutional Neural Network Model(Springer, 2018) Yousif, Abdallah; Niu, Zhendong; Nyamawe, Ally S.In the recent years, there has been an increased availability of scientific publications across the world connected through citations. To help analyze this huge amount of information, citation classification has been introduced to identify the opinions and purposes of the authors for citing earlier works. Existing approaches utilize machine learning techniques and report promising results in identifying the sentiment and purpose of the citations. However, most of the previous approaches tackle the citation sentiments and purposes classification in isolation. Moreover, they suffer from limited training data and time-consuming feature engineering process. In this paper, we address these issues by building a multitask learning model based on convolutional neural network. The proposed model jointly learns the citation sentiment classification (primary task) with the citation purpose classification as a related task to boost the classification performance. Experimental results on two public datasets show that our model outperforms the previous baseline methods and prove the effectiveness of multitask learning technique.Item A deep hybrid model for recommendation by jointly leveraging ratings, reviews and metadata information(Elsevier, 2021) Khan, Zahid Younas; Niu, Zhendong; Nyamawe, Ally S.; Haq, Ijaz ulAlthough matrix factorization (MF) based collaborative filtering (CF) and deep learning approaches have achieved great success, there is still much room for improvement in recommender systems. Most of the existing approaches mainly adopt product ratings, reviews or content features in order to predict unknown rating for a user–item pair. In the discourse matter, some recent works attempted to obtain better latent representations of users and items by integrating different multi-source data, however, the heterogeneity of data is still a problem deserving study. Such models usually face two issues: (1) They extract the representations in a static and independent manner, thus ignoring the correlations between latent features learned from different information sources. (2) There is no unified framework that can mutually learn latent features from different sources such as ratings, reviews and meta-data of users, items and reviews. In the proposed model, called A Deep Hybrid Model for Recommendation (DHMR), we propose a joint deep model for learning higher-order non-linear latent feature interactions from reviews and metadata information. Further, we incorporate user–item interactions (from user–item ratings matrix) adopting MF model into the neural network. Thus, the proposed model consists of two parallel neural networks and an MF based model that are integrated by the attention and MLP layers at the top, learning lower-order (linear and non-linear) feature interactions of users and items separately and higher-order non-linear feature interactions jointly. Extensive experiments on real-world datasets demonstrate that DHMR significantly outperforms state-of-the-art recommendation models.Item Fake review detection techniques, issues, and future research directions: a literature review(Springer Science and Business Media LLC, 2024) Duma, Ramadhani Ally; Niu, Zhendong; Nyamawe, Ally S.; Tchaye-Kondi, Jude; Jingili, Nuru; Yusuf, Abdulganiyu Abdu; Deve, Augustino FaustinoRecently, the impact of product or service reviews on customers' purchasing decisions has become increasingly significant in online businesses. Consequently, manipulating reviews for fame or profit has become prevalent, with some businesses resorting to paying fake reviewers to post spam reviews. Given the importance of reviews in decision-making, detecting fake reviews is crucial to ensure fair competition and sustainable e-business practices. Although significant efforts have been made in the last decade to distinguish credible reviews from fake ones, it remains challenging. Our literature review has identified several gaps in the existing research: (1) most fake review detection techniques have been proposed for high-resource languages such as English and Chinese, and few studies have investigated low-resource and multilingual fake review detection, (2) there is a lack of research on deceptive review detection for reviews based on language code-switching (code-mix), (3) current multi-feature integration techniques extract review representations independently, ignoring correlations between them, and (4) there is a lack of a consolidated model that can mutually learn from review emotion, coarse-grained (overall rating), and fine-grained (aspect ratings) features to supplement the problem of sentiment and overall rating inconsistency. In light of these gaps, this study aims to provide an in-depth literature analysis describing strengths and weaknesses, open issues, and future research directions.Item Harnessing the power of mobile phone technology to improve maternal healthcare in Tanzania: Proposed model(Foundation of Computer Science (FCS), 2014) Nyamawe, Ally S.; Seif, HassanIn the effort to reduce maternal mortality rate, Millennium Development Goal (MDG) 5 was declared globally. Tanzania has no exception on this. Maternal mortality and morbidity is still an enduring challenge in Tanzania. In 2010 the Maternal Mortality Rate (MMR) was recorded at 454/100,000 live births. Despite of the devoted efforts and significant progress that Tanzania has made in reducing MMR, still the situation demands for more improved intervention. One among the contributors of maternal mortality is lack of education to expectant mothers. In this paper, a model with a pivotal role to extend health information accessibility to expectant mothers is proposed. A proposed model is exploiting the potential and power of mobile phones to deliver its services. Existing extended network coverage and expansion of mobile phone usage are the unprecedented advantages that would also be exploited.Item Improving citation sentiment and purpose classification using hybrid deep neural network model(Springer, 2018) Yousif, Abdallah; Niu, Zhendong; Nyamawe, Ally S.; Hu, YatingAutomated citation classification has received much attention in recent years from the research community. It has many benefits in the bibliometric field such as improving the methods of measuring publications’ quality and productivity of the researchers. Most of the existing approaches are based on supervised learning techniques with discrete manual features to capture linguistic cues. Though these approaches have reported good results, extracting such features are time-consuming and may fail to encode the semantic meaning of the citation sentences, which consequently limits the classification performance. In this paper, a hybrid neural model is proposed, which combines convolutional and recurrent neural networks to capture local n-gram features and long-term dependencies of the text. The proposed model extracts the features automatically and classifies the sentiments and purposes of scientific citations. We conduct experiments using two publicly available datasets and the results show that our model outperforms previously reported results in terms of precision, recall, and F-score for citation classification.Item Leveraging the Power of Smartphones: Real Time Monitoring of Water Points(International Journal of Engineering Research and Applications ( IJERA), 2014) Nyamawe, Ally S.In recent years, the world has become more sophisticated. Different aspects of today’s life has been digitized, this include; business, education, health, communication and numerous community services. With the existing extended coverage of cellular networks, most services are constantly deployed to be accessed via mobile phones, as they are also the most pervasive pocket carried devices. Though, both regular and smartphone can be used to convey the basics of mobile based services such as mobile banking, calling and text messaging, smartphone goes extra mile. While regular phones are still the better choice for some, smartphones are tremendously taking over the cellphone market. Smartphones are powered by the vast amount of mobile apps available today which offer unprecedented features and functionalities and as well more advanced internet connectivity. To ensure reliable, sufficient and safe water supply to public, the installed water points need to be well monitored. Quality and quantity parameters of water produced from the water points are constantly tracked to determine if they are within the acceptable range. In case of acute condition, the identified parameters need to be instantly communicated to the District Water Engineer (DWE) for prompt intervention. In this paper we explore the popularity and advantages of smartphones and present a proposed prototype that exploit the power of smartphones in real time monitoring of water points.Item A new scheme for citation classification based on convolutional neural networks(KSI Research Inc, 2018) Bakhti, Khadidja; Niu, Zhendong; Nyamawe, Ally S.Automated classification of citation function in scientific text is a new emerging research topic inspired by traditional citation analysis in applied linguistic and scientometric fields. The aim is to classify citations in scholarly publication in order to identify author’s purpose or motivation for quoting or citing a particular paper. Several citation schemes have been proposed to classify the citations into different functions. However, it is extremely challenging to find standard scheme to classify citations, and some of the proposed schemes have similar functions. Moreover, most of previous studies mainly used classical machine learning methods such as support vector machine and neural networks with a number of manually created features. These features are incomplete and suffer from time-consuming and error prone weakness. To address these problems, we present a new citation scheme with less functions and propose a deep learning model for classification. The citation sentences and author’s information were fed to convolutional neural networks to build citation and author representations. A corpus was built using the proposed scheme and a number of experiments were carried out to assess the model. Experimental results have shown that the proposed approach outperforms the existing methods in term of accuracy, precision and recallItem On the Impact of Refactorings on Software Attack Surface(Institute of Electrical and Electronics Engineers (IEEE), 2024) Edward, Estomii; Nyamawe, Ally S.; Elisa, NoeRefactoring is one of the techniques mostly employed by software developers to improve the quality attributes of their systems. However, little has been done to investigate how refactoring operations specifically aimed at improving the internal structure of software can impact its security. Refactoring usually entails different code change operations including the decomposition of classes, methods, and the reallocation of code elements. While this refinement aims to improve the internal design of a system, it might inadvertently disperse security-critical code elements throughout the codebase. Consequently, such dispersion could affect the software attack surface. To this end, this paper presents an empirical study of 30 open-source software systems developed in Python, C, and Javascript. The study scrutinized two subsequent versions of each subject application to uncover the refactoring operations applied and the trend of the software attack surface. Specifically, the study focused on the injection or removal of bugs, code smells and other vulnerabilities aiming to discern the impact of refactorings on the software attack surface. Data was collected using wellknown tools, namely SonarQube, RefDiff, and PyReff. The findings suggest that refactorings can have multiple impacts (i.e., positive, negative, or neutral) on bugs, code smells, and vulnerabilities. The findings further confirm that developers must be aware of the combination or sequence of refactoring operations that can improve software quality without compromising its securityItem A proposed framework for development of a visualizer based on memory transfer language (MTL)(International Journal of Computer Trends and Technology (IJCTT), 2014) Nyamawe, Ally S.Computer programming is among the fundamental aspects of computer science curriculum. Many students first introduced to introductory computer programming courses experience difficulties in learning and comprehending. Vast amount of researches have revealed that, generally programming courses are regarded as difficult and challenging and thus often have the highest dropout rates. Moreover, numerous researches have devoted in delivering new approaches and tools in enhancing the process of teaching and learning computer programming to novice programmers. One among the tools that have emerged to offer positive results is Program Visualization tool (Visualizer). Visualizers have shown remarkable contributions in facilitating novices to learn and comprehend computer programming. In addition to that, an approach to visualize codes execution, Memory Transfer Language (MTL), allows a novice to animate the code through paper and pencil mechanism without actively involving the machine. MTL depends on the concepts of RAM (Random Access Memory) to interpret the code line by line. Programming requires effort and special approach in the way it is learned and taught, thus this paper aimed at presenting a proposed framework for developing a visualizer that employs the use of MTL to enhance teaching and learning programming.Item Road Safety: Adoption of ICT for Tracking Vehicles’ Over-speeding in Tanzania(Foundation of Computer Science (FCS), 2014) Nyamawe, Ally S.; Mbosso, Emmanuel C.The number of road incidents which result to deaths, injury, disabilities and loss of property is frightening. In Tanzania, the major contributor of road accidents is human factor which account for 74% in 2010. Vehicles’ over-speeding is named to be one of the accelerating factors to the increase of road casualties. The existing measures to limit over-speeding has not shown major contribution to the road safety as there are only countable inspection points with speed radar guns as a way to limit over-speeding. This paper discusses the adoption of ICT for tracking vehicles and proposes the model for tracking in real time vehicles’ over-speeding in Tanzania.Item The role of ICT in reducing maternal and neonatal mortality rate in Tanzania(Foundation of Computer Science (FCS), 2014) Nyamawe, Ally S.; Seif, HassanTanzania is striving to achieve Millennium Development Goals (MDG) 4 and 5 that call for reducing Neonatal and Maternal Mortality Rate (MNMR) by 2015. In 2010, Neonatal Mortality Rate (NMR) was recorded at 51 per 1,000 live births and Maternal Mortality Rate (MMR) at 454 per 100,000 live births. Despite of the devoted efforts and significant progress, still the mortality rate needs attention and effective intervention to cut it down considerably. The capability and power of Information and Communication Technology (ICT) need to be effectively exploited in revolutionizing health sector in Tanzania. The witnessed expansion of mobile phones usage and extended network coverage presents potential opportunity in enhancing quality of Maternal, Neonatal and Child Health (MNCH) services delivery. This paper explores the role of ICT in reducing MMR and NMR, existing solutions are intensely reviewed to discover what is lacking and provide necessary recommendations.Item Semi-automatic annotation for citation function classification(Institute of Electrical and Electronics Engineers ( IEEE), 2018) Bakhti, Khadidja; Niu, Zhendong; Nyamawe, Ally S.Citation function classification generally is a way to classify citations into different functions. Commonly, functions are used to determine authors purposes of citing a particular paper. Automated classification of citation functions plays a significant role in increasing educational use of citation function in scholarly publication. Due to varied informative citation, many researchers are experiencing difficulties in retrieving automatically the nature of the citations that meet their research needs. In addition, corpus builders demand tools and models that will help them carry out citation functions annotation effectively. Most of previous studies annotated the citations manually in different ways, which is often time-consuming and domain dependent. To overcome these challenges, in this paper we propose new semi-automatic annotation for citation functions classification. The proposed approach builds an annotated corpus from the citation sentences. The effectiveness of the approach is compared with existing machine-learning methods. The results indicate that our approach outperforms other methods in terms of accuracy, precision and recall.Item SES-Net: A Novel Multi-Task Deep Neural Network Model for Analyzing E-learning Users’ Satisfaction via Sentiment, Emotion, and Semantic(Informa UK Limited, 2024) Sandiwarno, Sulis; Niu, Zhendong; Nyamawe, Ally S.Abstract Understanding users’ satisfaction is fundamental for enhancing the effectiveness and usability of e-learning platforms. The existing approaches for analyzing users’ satisfaction leverage word embedding vectors to represent sentiment information, but they often fail to fully address the complex relationship between emotional and semantic information. Additionally, several emotional and semantic word embedding models are proposed, but they require sentiment information. In this study, we propose a novel multi-task deep neural model, called Sentiment-Emotion-Semantic Network (SES-Net), capable of learning sentiment, emotion, and semantic information simultaneously. The proposed model comprises three main sub-neural tasks: Bidirectional Long Short-Term Memory (BiLSTM) to capture sentiment, BiLSTM to extract semantics, and Convolutional Neural Networks (CNN) to learn emotional features. Experimental results reveal that, SES-Net outperforms the previous approaches by achieving an average F1-score of 90.59%.Item The use of mobile phones in university exams cheating: proposed solution(Seventh Sense Research Group, 2014) Nyamawe, Ally S.; Mtonyole, NixonCurrently, instant communication is very possible all over the world due to a rapid growth in mobile phones technology. Each day, a number of mobile phones subscribers and cellular network coverage is escalating tremendously. Today’s mobile phones are released with ability nearly to that of a desktop computer. The ubiquity nature of mobile phones and extended network coverage allows for constant connectivity, easy flow of information and accessibility. Students use mobile phones to store lecture materials, tutorials, communicate with colleagues and surf the internet for different purposes. These advantages would have adverse effects if mobile phones will be brought in restricted premises such as exam venues. Disobedient candidates use mobile phones to cheat in exams. In this paper, we propose a system prototype that will be used to detect mobile phones in the exam venues.