Browsing by Author "Salman, Abdulsalam Abiodun"

Now showing 1 - 3 of 3
  • Item
    Heterogeneous ensemble with combined dimensionality reduction for social spam detection
    (International Association of Online Engineering, 2021) Oladepo, Abdulfatai Ganiyu; Bajeh, Amos Orenyi; Balogun, Abdullateef Oluwagbemiga; Mojeed, Hammed Adeleye; Salman, Abdulsalam Abiodun; Bako, Abdullateef Iyanda
    Spamming is one of the challenging problems within social networks which involves spreading malicious or scam content on a network; this often leads to a huge loss in the value of real-time social network services, compromise the user and system reputation and jeopardize users trust in the system. Existing methods in spam detection still suffer from misclassification caused by redundant and irrelevant features in the dataset as a result of high dimensionality. This study presents a novel framework based on a heterogeneous ensemble method and a hybrid dimensionality reduction technique for spam detection in micro-blogging social networks. A hybrid of Information Gain (IG) and Principal Component Analysis (PCA) (dimensionality reduction) was implemented for the selection of important features and a heterogeneous ensemble consisting of Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR) and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) classifiers based on Average of Probabilities (AOP) was used for spam detection. To empirically investigate its performance, the proposed framework was applied on MPI_SWS and SAC’13 Tip spam datasets and the developed models were evaluated based on accuracy, precision, recall, f-measure, and area under the curve (AUC). From the experimental results, the proposed framework (Ensemble + IG + PCA)outperformed other experimented methods on studied spam datasets. Specifically, the proposed framework had an average accuracy value of 87.5%, an average precision score of 0.877, an average recall value of 0.845, an average F-measure value of 0.872 and an average AUC value of 0.943. Also, the proposed framework had better performance than some existing approaches. Consequently, this study has shown that addressing high dimensionality in spam datasets, in this case, a hybrid of IG and PCA with a heterogeneous ensemble method can produce a more effective model for detecting spam contents.
  • Item
    Proposed Model for Information Access Using Web 2.0 as Platform for Sustainable Development
    (Faculty of Communication and Information Sciences, University of Ilorin., 2019-05) Olajide, A.A.; Salman, Abdulsalam Abiodun
    Development has always been a product of information or knowledge produced. Sustaining the development is the aspiration of any organization. Today as a result of lack of access to information; sustaining development is a bit challenging. Web 2.0 has come to the rescue of accessibility of information and at the same time a platform for information and knowledge. It has also been discovered that web 2.0 possess various characteristics that made it a suitable platform for information processing to achieve development. Sustaining the development is now possible on Web 2.0 due to some of its characteristics and the fact that information is better spread and processed on it. The model proposed showed that Web 2.0 is appropriate for information and knowledge accessibility and management with the antedate outcome as sustainable development.
  • Item
    Undergraduate Students’ Preference for Web-based and Conventional Library Services in Kwara State University, Malete, Kwara State, Nigeria
    (Faculty of Communication and Information Sciences, University of Ilorin., 2018-12-02) Salman, Abdulsalam Abiodun; Aleem, Abdulmalik Oyindamola
    The purpose of this study is to investigate undergraduate students’ preference for web-based and conventional library services in Kwara State University. Specifically, the study aimed at identifying the types of web based and conventional library services available, and also determines the frequency with which the students are using web-based and conventional library services in the University. The study adopted descriptive survey design. The population of the study was 3,572 undergraduate library users out of which a sample of three hundred and forty-six (346) was selected using convenience sampling technique. Three hundred and twenty (320) respondents, representing 92.5% of the sample size returned their questionnaire. The questionnaire is titled “Undergraduate Students’ Preference for Web-based and Conventional Library Services” and was used to gather data from the respondents. Data collected were examined and analysed using frequency count and percentage while t-test was used to test the only null hypothesis of the study. The findings of the study showed that 95.9% of the respondents attested to the availability of web based library services. Also, 58.4% of respondents preferred Frequently Ask Questions (FAQ) as integral part of web based library services. In the same vein, the study also discovered that 93.3% of the respondent utilized library orientation and instruction services, while current awareness service is the least or rarely used conventional library services representing 41.9%. Cumulatively, the study discovered that web based library services are the most preferred services used by the students. The study recommended that university authority and library management should make provision and further advocate the use of web based library services, while the conventional services serve as complimentary. This is pertinent in order to conform to global modern library practice which is characterized by using ICT facilities and resources.