Faridah Hani Mohamed Salleh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Faridah Hani Mohamed Salleh has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Deshinta Arrova Dewi
Center for Data Science and Sustainable Technologies, INTI International University, Nilai, Malaysia
3 shared publications - Ahmad Ikhsan Abdul Aziz
Universiti Tenaga Nasional
1 shared publication Deshinta Arrova Dewi
INTI International University
1 shared publication- Gunasekaran
Universiti Tenaga Nasional
1 shared publication - Husni Mohd Radzi
Universiti Tenaga Nasional
1 shared publication - Loi Ming Low
Universiti Tenaga Nasional
1 shared publication
Latest Publications
- 12 July 2025
- Published by Springer Nature
- p. 97-109
AI-Based Mobile Application for the Visually Impaired Community
- 12 July 2025
- Published by Springer Nature
- p. 97-109
AI-Based Mobile Application for the Visually Impaired Community
- 3 September 2024
- Published by Springer Nature
- p. 675-691
Formulation of an AI-Based Call Analytics Model for Analysing Mixed-Language Customer Calls
- 3 September 2024
- Published by Springer Nature
- p. 675-691
Formulation of an AI-Based Call Analytics Model for Analysing Mixed-Language Customer Calls
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 122, 420-425
Sentiment Analysis on Mixed-Language Social Media Post
Sentiment analysis is a powerful tool that can be used by businesses and organizations to gather valuable data about public opinion towards a brand, product, topic, event, and much more. However, most Malaysians post on social media using a mix of English and Malay words, also known as Manglish, which are not catered to by existing sentiment analysis models. Malaysian-centric companies that are interested to analyze the Malaysian posts would have to do so manually, which is costly and time-consuming. Motivated by this issue, this paper aims to propose a method of performing sentiment analysis on posts using the power of machine learning. Several machine learning algorithms were identified and trained to classify a Manglish post as either positive or negative. Steps are also taken to ensure the reliability of the model and to improve it after the first training experiment. We found that this method is successful in producing a model that can predict social media post sentiment with reliable and acceptable accuracy.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 122, 420-425
Sentiment Analysis on Mixed-Language Social Media Post
Sentiment analysis is a powerful tool that can be used by businesses and organizations to gather valuable data about public opinion towards a brand, product, topic, event, and much more. However, most Malaysians post on social media using a mix of English and Malay words, also known as Manglish, which are not catered to by existing sentiment analysis models. Malaysian-centric companies that are interested to analyze the Malaysian posts would have to do so manually, which is costly and time-consuming. Motivated by this issue, this paper aims to propose a method of performing sentiment analysis on posts using the power of machine learning. Several machine learning algorithms were identified and trained to classify a Manglish post as either positive or negative. Steps are also taken to ensure the reliability of the model and to improve it after the first training experiment. We found that this method is successful in producing a model that can predict social media post sentiment with reliable and acceptable accuracy.
- 27 April 2023
- Published by Springer Nature
- p. 305-315
Student’s Mental Health Diagnostic Expert System Using DASS Analysis and Rule-Based Reasoning: A Proposal
- 27 April 2023
- Published by Springer Nature
- p. 305-315
Student’s Mental Health Diagnostic Expert System Using DASS Analysis and Rule-Based Reasoning: A Proposal
- 16 November 2021
- Published by Springer Nature
- p. 362-373
A Model for Teaching and Learning Programming Subjects in Public Secondary Schools of Malaysia
- 16 November 2021
- Published by Springer Nature
- p. 362-373
A Model for Teaching and Learning Programming Subjects in Public Secondary Schools of Malaysia
- Open Access
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1878 (1) , 012067
Evaluating the Effectiveness of Course Assessments Method in Determining Student’s Competency Level in Programming
Students who choose to study in Computer Science in Malaysia at the Degree level, basically have a diverse background of academic achievement at the final level of their secondary school. Although there are minimum requirements set for admission to Computer Science courses, students tend to demonstrate different achievements after being at university. It is possible that the method of evaluation of educational institutions is not in line with the actual skills mastered by the students. Therefore, this study takes all the test data that has been collected before and assesses which type of test is actually most effective to determine the level of student’s competency in programming. This study proves that compared to other type of assessments, students’ achievement in the final examination, additional lab assessment with challenging questions and test correlated positively with the student’s programming competency. Our experiments also prove that if the final exam score is less than 60%, it is very likely that the student should be classified as incompetent. This suggests the final exam marks should carry significant weightage so that students do not just rely on carried marks to get a high grade.
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1878 (1) , 012067
Open AccessEvaluating the Effectiveness of Course Assessments Method in Determining Student’s Competency Level in Programming
Students who choose to study in Computer Science in Malaysia at the Degree level, basically have a diverse background of academic achievement at the final level of their secondary school. Although there are minimum requirements set for admission to Computer Science courses, students tend to demonstrate different achievements after being at university. It is possible that the method of evaluation of educational institutions is not in line with the actual skills mastered by the students. Therefore, this study takes all the test data that has been collected before and assesses which type of test is actually most effective to determine the level of student’s competency in programming. This study proves that compared to other type of assessments, students’ achievement in the final examination, additional lab assessment with challenging questions and test correlated positively with the student’s programming competency. Our experiments also prove that if the final exam score is less than 60%, it is very likely that the student should be classified as incompetent. This suggests the final exam marks should carry significant weightage so that students do not just rely on carried marks to get a high grade.
- 16 March 2021
- Published by Springer Nature
- Vol. 724, 501-513
Issues and Challenges for Teaching Successful Programming Courses at National Secondary Schools of Malaysia
Undoubtedly, the initiative of the Malaysia education ministry to introduce coding in school curricula is a very good effort with lots of advantages. Able to code will be an advantage and a necessity when the students join the workforce. After not small amount of budget and time has been spent by the country for this mission, there are several issues that need to be considered and worked on to ensure coding lessons in schools achieves the target. This paper presents six issues and the recommended solutions that do not require a change to the current educations system as frequent changes in national education policy will burden teachers, parents and students. The identified issues are from the perspective of language of communication, implementation and execution, digital divide, quality tools, assessments and teaching and learning time. This works suggests to create a self-learning system built specifically for the national secondary schools’ syllabus, short-term job exemption for teachers and programming skill test to replace project as part of assessments to increase the rate of teaching effectiveness of Computer Science subjects, especially programming. This study will be of great important to educational planners, school authorities, educational researchers and the governments.
- 16 March 2021
- Published by Springer Nature
- Vol. 724, 501-513
Issues and Challenges for Teaching Successful Programming Courses at National Secondary Schools of Malaysia
Undoubtedly, the initiative of the Malaysia education ministry to introduce coding in school curricula is a very good effort with lots of advantages. Able to code will be an advantage and a necessity when the students join the workforce. After not small amount of budget and time has been spent by the country for this mission, there are several issues that need to be considered and worked on to ensure coding lessons in schools achieves the target. This paper presents six issues and the recommended solutions that do not require a change to the current educations system as frequent changes in national education policy will burden teachers, parents and students. The identified issues are from the perspective of language of communication, implementation and execution, digital divide, quality tools, assessments and teaching and learning time. This works suggests to create a self-learning system built specifically for the national secondary schools’ syllabus, short-term job exemption for teachers and programming skill test to replace project as part of assessments to increase the rate of teaching effectiveness of Computer Science subjects, especially programming. This study will be of great important to educational planners, school authorities, educational researchers and the governments.
- Open Access
- 29 January 2017
- Published by Wiley in Advances in Bioinformatics
- Vol. 2017, 1-14
Multiple Linear Regression for Reconstruction of Gene Regulatory Networks in Solving Cascade Error Problems
Gene regulatory network (GRN) reconstruction is the process of identifying regulatory gene interactions from experimental data through computational analysis. One of the main reasons for the reduced performance of previous GRN methods had been inaccurate prediction of cascade motifs. Cascade error is defined as the wrong prediction of cascade motifs, where an indirect interaction is misinterpreted as a direct interaction. Despite the active research on various GRN prediction methods, the discussion on specific methods to solve problems related to cascade errors is still lacking. In fact, the experiments conducted by the past studies were not specifically geared towards proving the ability of GRN prediction methods in avoiding the occurrences of cascade errors. Hence, this research aims to propose Multiple Linear Regression (MLR) to infer GRN from gene expression data and to avoid wrongly inferring of an indirect interaction (A → B → C) as a direct interaction (A → C). Since the number of observations of the real experiment datasets was far less than the number of predictors, some predictors were eliminated by extracting the random subnetworks from global interaction networks via an established extraction method. In addition, the experiment was extended to assess the effectiveness of MLR in dealing with cascade error by using a novel experimental procedure that had been proposed in this work. The experiment revealed that the number of cascade errors had been very minimal. Apart from that, the Belsley collinearity test proved that multicollinearity did affect the datasets used in this experiment greatly. All the tested subnetworks obtained satisfactory results, with AUROC values above 0.5.
- 29 January 2017
- Published by Wiley in Advances in Bioinformatics
- Vol. 2017, 1-14
Open AccessMultiple Linear Regression for Reconstruction of Gene Regulatory Networks in Solving Cascade Error Problems
Gene regulatory network (GRN) reconstruction is the process of identifying regulatory gene interactions from experimental data through computational analysis. One of the main reasons for the reduced performance of previous GRN methods had been inaccurate prediction of cascade motifs. Cascade error is defined as the wrong prediction of cascade motifs, where an indirect interaction is misinterpreted as a direct interaction. Despite the active research on various GRN prediction methods, the discussion on specific methods to solve problems related to cascade errors is still lacking. In fact, the experiments conducted by the past studies were not specifically geared towards proving the ability of GRN prediction methods in avoiding the occurrences of cascade errors. Hence, this research aims to propose Multiple Linear Regression (MLR) to infer GRN from gene expression data and to avoid wrongly inferring of an indirect interaction (A → B → C) as a direct interaction (A → C). Since the number of observations of the real experiment datasets was far less than the number of predictors, some predictors were eliminated by extracting the random subnetworks from global interaction networks via an established extraction method. In addition, the experiment was extended to assess the effectiveness of MLR in dealing with cascade error by using a novel experimental procedure that had been proposed in this work. The experiment revealed that the number of cascade errors had been very minimal. Apart from that, the Belsley collinearity test proved that multicollinearity did affect the datasets used in this experiment greatly. All the tested subnetworks obtained satisfactory results, with AUROC values above 0.5.
- 1 December 2015
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 59, 3-14
Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient
- 1 December 2015
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 59, 3-14
Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient