PhD
Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/35
This collection archives the complete set of theses produced by students of the COMSATS University Islamabad, Lahore Campus.
Browse
3 results
Search Results
Item Spam Review Detection through Behavioral and Linguistic Approaches(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Naveed Hussain; FA15-PCS-002; LHR TP 7730Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are ex tremely concerned with customer reviews as these have a direct impact on their busi nesses. Unfortunately, to gain profits or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In last few years, the Spam Review Detection (SRD) problem has gained much attention from communities and researchers, but there is still a need to introduce new spam re view detection methods to improve accuracy results utilizing real-world datasets. To overcome these problems, three methods have been proposed. In the first framework, two different spam review detection methods have been pro posed: (i) Spam Review Detection using Behavioral Method (SRD-BM) utilizes thir teen different spammer’s behavioral features to calculate the review spam score which is then used to identify spammers and spam reviews, and (ii) Spam Review Detection using Linguistic Method (SRD-LM) works on the content of the reviews and utilizes transformation, feature selection and classification to identify the spam reviews. Exper imental evaluations are conducted on a real-world Amazon review dataset which ana lyzes 26.7 million reviews and 15.4 million reviewers. The evaluations show that both proposed methods have significantly improved the detection process of spam reviews. Specifically, SRD-BM achieved 93.1% accuracy whereas SRD-LM achieved 88.5% accuracy in spam review detection. Comparatively, SRD-BM achieved better accuracy because it works on utilizing a rich set of spammers’ behavioral features of review da taset which provides in-depth analysis of spammer behavior. Moreover, both proposed methods outperformed existing approaches when compared in terms of accurate iden tification of spam reviews. To the best of the researcher’ knowledge, this is the first study of its kind which uses a large-scale review dataset to analyze different spammers’ behavioral features and linguistic methods utilizing different available classifiers. xi The second method has been developed to analyze the Roman Urdu review dataset based on different classification techniques utilizing linguistic and behavioral features. The performance of each classifier is evaluated in several perspectives: (i) Linguistic features are used to calculate accuracy (F1 Score) of each classifier; (ii) Behavioral features combined with distributional and non-distributional aspects are used to evalu ate accuracy (F1 Score) of each classifier; and (iii) The combination of both linguistic and behavioral features (distributional and non-distributional aspects) are used to eval uate the accuracy of each classifier. The experimental evaluations demonstrated an im proved accuracy (F1 Score: 0.96), which is the result of combinations of linguistic fea tures and behavioral features with the distributional aspect of reviewers. Moreover, be havioral features using distributional characteristic achieved an accuracy (F1 Score) of 0.86 and linguistic features shows an accuracy (F1 Score) of 0.69. The outcome of this research can be used to increase customers’ confidence on online reviews in the South Asian region. It can also help to reduce spam reviews in the South Asian region, partic ularly in Pakistan. The third method proposed Spammer Group Detection (SGD) method, which iden tifies suspicious spammer groups based on the similarity of all reviewer’s activities. Deep learning classifiers are used for training and testing the proposed SGD method. The study also proposed the Diversified Set of Reviews (DSR) method which presents a diversified set of top-k non-spam reviews having positive, negative, and neutral sen timents. Furthermore, it covers all possible features about the product or service. Ex perimental evaluations are conducted on daraz.pk and yelp.com real-world review da tasets. It has been observed by experimental analysis that the proposed SGD method has achieved 89.41% accuracy for the Yelp dataset and 81.31% accuracy for the Daraz dataset in detecting suspicious spammer groups and spam reviews.Item Multilingual Source Code Analysis for Recovery of J2EE Environment(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2017) Zaigham Mushtaq; SP11-PCS-001; LHR TP 5940; Dr. Ghulam RasoolDesign patterns are proven solutions that help to develop quality software applications and program comprehension at the design level. Recovering design information from source code supports source code analysis for better program understanding, reuse, and re-engineering. With the advent of modern technologies in software development paradigm, the size and complexity of software applications are increased, consequently, extracting software design has become harder and challenging. In these multilingual applications, the design information is scattered in various cross-language artifacts that are interdependent on each other. Therefore, in order to analyze these applications, all the cross-language components and their relationships needs to be resolved. At present, there is no approach known to us that is capable of extracting design information from multilingual applications by using design patterns. The purpose of this thesis is to build the foundation for the analysis of multilingual applications by using design patterns. Java Enterprise Applications are the examples of multilingual applications i.e. their design information is scattered in several multilingual artifacts. This platform is equipped with verified design solutions in the form of J2EE Patterns. J2EE Platform is a multi-tiered architecture. The instances of these patterns are scattered in various cross language components in different layers of J2EE Platform. It is difficult to resolve cross-language artifacts and extract desirable information and dependencies. J2EE Patterns have abstract representations and their formal definitions are not known. In addition, to the best of our insight, there is no approach available to recognize J2EE Patterns from Java enterprise applications. In this dissertation, a novel approach is presented for the detection of J2EE Patterns from the multilingual source code of J2EE applications. For this purpose, customizable and reusable feature types are presented as a catalog of J2EE Pattern definitions. These feature types can accommodate new pattern definitions and are adaptable to detect the variants of any pattern. A prototype toolkit, JPDT (J2EE Pattern Detection Tool) is developed that uses J2EE Pattern definitions based on a catalog of customizable feature types and extracts J2EE Patterns from the multilingual source code of enterprise applications. This tool has three xi basic components; including J2EE Extended Parsing Module (JPSP), J2EE Pattern Detection Engine (JPDE) and J2EE Patterns Visualization Module (JPVM). In order to evaluate the validity of approach and prototype tool, a corpus is built that contains the repository of the source code of J2EE Pattern definitions. Additionally, the tool is evaluated on five open source medium and large enterprise applications. The results reveal 100 % accuracy of approach in successful recognition of J2EE Patterns in source code repository and open source applications. The results also establish the significance of customizable definitions of J2EE Pattern’s catalog and capability of prototype toolItem Computer Vision Based Pattern Matching and Displacement Detection During Fabric Printing(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2017) Muhammad Abdul Qayum; FA10-PCS-001; LHR TP 5799; Dr. Farooq AhmadThere is an absolute need for the robust quality inspection system, which can take on the new challenges and overcome the human limitations to inspect the fabric production consistently. To address this gap, computer vision based techniques are employed by enterprises. Some of the beneficent manufacturers include ceramic, circuit board printer, paper printer and textiles. Excellent work has been done in the yarn and weaving production sections of textile industry, however fabric printing monitoring is being explored by the researchers. The referential approach is mostly adopted to monitor fabric printing for defect detection. It works by acquiring an error-free image and registering this image with subsequent images captured during the production. In this method, the major time-consuming problem is to find the design repeat in the sample image before further processing. The researchers suggested some methods like distance matching in RGB space, photo encoders, genetic algorithm along with recursive splitting, Fuzzy C-means clustering, and cross correlation algorithm. There are certain limitations with these methods, for instance, sensitive to small deformation, required extra hardware prone to mechanical fault and it is expensive in calculations. In this research, a method for finding the design repeat is proposed. The method is tuned up according to the textile printing domain. Since the fabric moves in one direction during printing process, therefore the image registration can be confined to the same direction. To further speed up the process, the image registration method is applied using few initial pixel columns of the reference image with the sample image. Such bunch of selected columns of the reference image is matched with the same number of columns selected from sample image by moving this bunch on the sample image column by column. The maximum matching position is marked as the start of the design repeat. As the repeat size is always fixed, therefore complete design can be extracted from acquired image for defect detection. The experimental results on different fabric designs using the above-mentioned method are promising. Moreover, xi this technique improves the image alignment speed which enhances defect detection system performance. The most common defect is the displacement or misregistration of a colour. This defect is caused by the misalignment of cylindrical screens of fabric printing machine. As every screen is responsible for a colour, the misaligned screen registers the colour on the incorrect position. It leads to defective production and contributes to a substantial loss of the material and time. Few researchers proposed the feature based solution which are either computationally expensive or do not provide detail information about the defect like location and colour. Further, some techniques depend on the additional algorithms to find defects. Mostly, these methods depend on the accuracy of reference and sample image alignment. So there is always a chance of wrong notification. An improved algorithm for the detection of displacement of a colour during fabric printing is proposed in this thesis. The algorithm concatenates red, green and blue pixel values of the RGB image to represent a colour and later produces a frequency distribution of different colours for both sample and reference images. The colours with low frequencies are removed considering noise. In the next step, colours are grouped depending upon their distances from each other. These colour groups are later used to detect any new colour in the sample image which is actually created by the displacement defect and colour variation. The proposed algorithm successfully detects displacement and colour variation defects when it is tested using different flawed printed fabric images. The result shows that the proposed method has almost same accuracy as stat of the art algorithm and more helpful to detect the colour displacement, and it can also overcome the shortcoming of repeat finding process.