Majdah Alvi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Majdah Alvi has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Bux Alvi
Department of Computer Systems Engineering, The Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan
4 shared publications - Noor Fatima
Department of Computer Systems Engineering, Faculty of Engineering, The Islamia University of Bahawalpur, Punjab, Pakistan
2 shared publications - Adnan Akhter
Department of Computer Systems Engineering, Faculty of Engineering, The Islamia University of Bahawalpur, Punjab, Pakistan
1 shared publication Fatima Noor
Islamia University of Bahawalpur
1 shared publicationKavita Tabassum
Sindh Agriculture University
1 shared publicationKazim Jawad
Islamia University of Bahawalpur
1 shared publication
Latest Publications
- Open Access
- 13 October 2025
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 12 (5)
Life Expectancy Prediction using Recursive Partitioning and Bagging Algorithms
Life expectancy is a crucial indicator of the population’s health and well-being. Recent research has highlighted the importance of various socioeconomic and health factors in determining the lifespan of individuals. Those factors include Gross Domestic Product (GDP), healthcare expenditure, mortality rates, and education level. This study employs recursive partitioning (decision trees) and bagging (random forest) techniques on the Life Expectancy dataset from the World Health Organization (WHO) to evaluate theeffectiveness of predictive models. The dataset was prepared by encoding categorical features, scaling the features, normalizing them, and handling outliers. Mean imputation was used to handle missing values and produce a quality dataset. Optimized models based on recursive partitioning and bagging algorithms achieved performance efficiencies of 92% and 97%, respectively. The bagging algorithm-based model produced a mean squared error of 1.17, a mean absolute error of 2.0, and an R2-score of 97%. Other key findings included the importance of dataset characteristics—such as HIV/AIDS prevalence, adult mortality, and health resource income—in predicting life expectancy. This research elucidates the impact of feature engineering and data preprocessing strategies on data quality and predictive model precision, offering novel insights for public health policymaking and informing future research directions.
- 13 October 2025
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 12 (5)
Open AccessLife Expectancy Prediction using Recursive Partitioning and Bagging Algorithms
Life expectancy is a crucial indicator of the population’s health and well-being. Recent research has highlighted the importance of various socioeconomic and health factors in determining the lifespan of individuals. Those factors include Gross Domestic Product (GDP), healthcare expenditure, mortality rates, and education level. This study employs recursive partitioning (decision trees) and bagging (random forest) techniques on the Life Expectancy dataset from the World Health Organization (WHO) to evaluate theeffectiveness of predictive models. The dataset was prepared by encoding categorical features, scaling the features, normalizing them, and handling outliers. Mean imputation was used to handle missing values and produce a quality dataset. Optimized models based on recursive partitioning and bagging algorithms achieved performance efficiencies of 92% and 97%, respectively. The bagging algorithm-based model produced a mean squared error of 1.17, a mean absolute error of 2.0, and an R2-score of 97%. Other key findings included the importance of dataset characteristics—such as HIV/AIDS prevalence, adult mortality, and health resource income—in predicting life expectancy. This research elucidates the impact of feature engineering and data preprocessing strategies on data quality and predictive model precision, offering novel insights for public health policymaking and informing future research directions.
- Open Access
- 3 May 2025
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 13 (2) , 28-43
Emotion Detection and Analysis using Textual Data through Trainable and Pre-trained Word Embedding Methods
Emotion expression modes play a significant role in human communication. Humans use emotions to convey their state of mind to each other on platforms such as X (formerly Twitter), Facebook, and other online social networks. People often express their emotions using free text, which triggers a vast research area of emotion detection and analysis. This work aims to detect and analyze emotions from unstructured text data. For this purpose, this research study proposes a solution to the problem by building a deep artificial neural network model using trainable and pre-trained word embedding methods. Afterward, the performance of the models developed with different word embeddings is evaluated using the performance metrics. Experimental works demonstrate that the deep artificial neural network with trainable word embedding surpassed all other models by achieving 67.36% accuracy, 53.27% recall, 82.62% precision, and 64.50% F-measure.
- 3 May 2025
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 13 (2) , 28-43
Open AccessEmotion Detection and Analysis using Textual Data through Trainable and Pre-trained Word Embedding Methods
Emotion expression modes play a significant role in human communication. Humans use emotions to convey their state of mind to each other on platforms such as X (formerly Twitter), Facebook, and other online social networks. People often express their emotions using free text, which triggers a vast research area of emotion detection and analysis. This work aims to detect and analyze emotions from unstructured text data. For this purpose, this research study proposes a solution to the problem by building a deep artificial neural network model using trainable and pre-trained word embedding methods. Afterward, the performance of the models developed with different word embeddings is evaluated using the performance metrics. Experimental works demonstrate that the deep artificial neural network with trainable word embedding surpassed all other models by achieving 67.36% accuracy, 53.27% recall, 82.62% precision, and 64.50% F-measure.
- Open Access
- 31 December 2024
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 12 (2) , 285-297
Empowering Sentiment Analysis with Deep Learning Model: Evaluating Social Media's Benefits and Drawbacks
Online social networks (OSNs) have revolutionized communication by facilitating unprecedented information sharing and global connections. Despite these benefits, OSNs also present significant challenges, including the spread of misinformation, increased distraction, and adverse mental health effects. This study examines a dataset of 3,904 user reviews collected from online sources and personal networks, revealing a polarized sentiment distribution with 56% positive, 43.1% negative and 0.9% neutral views on the impact of social platforms. To capture the nuanced sentiments expressed, Long Short-Term Memory (LSTM) enhanced with preprocessing techniques such as tokenization, lemmatization, and word embeddings with Word2Vec was employed. The LSTM model achieved an accuracy of 86.43% in sentiment classification, significantly outperforming traditional baseline methods. These findings provide valuable information for platform developers, policymakers, and researchers aiming to understand and mitigate the social and psychological effects of digital platforms. Future research will focus on expanding the dataset and addressing class imbalance to further refine and enhance sentiment analysis models.
- 31 December 2024
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 12 (2) , 285-297
Open AccessEmpowering Sentiment Analysis with Deep Learning Model: Evaluating Social Media's Benefits and Drawbacks
Online social networks (OSNs) have revolutionized communication by facilitating unprecedented information sharing and global connections. Despite these benefits, OSNs also present significant challenges, including the spread of misinformation, increased distraction, and adverse mental health effects. This study examines a dataset of 3,904 user reviews collected from online sources and personal networks, revealing a polarized sentiment distribution with 56% positive, 43.1% negative and 0.9% neutral views on the impact of social platforms. To capture the nuanced sentiments expressed, Long Short-Term Memory (LSTM) enhanced with preprocessing techniques such as tokenization, lemmatization, and word embeddings with Word2Vec was employed. The LSTM model achieved an accuracy of 86.43% in sentiment classification, significantly outperforming traditional baseline methods. These findings provide valuable information for platform developers, policymakers, and researchers aiming to understand and mitigate the social and psychological effects of digital platforms. Future research will focus on expanding the dataset and addressing class imbalance to further refine and enhance sentiment analysis models.
- Open Access
- 13 January 2023
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- p. e10
Google Maps Data Analysis of Clothing Brands in South Punjab, Pakistan
The Internet is a popular and first-hand source of data about products and services. Before buying a product, people try to gain quick insight by scanning through online reviews about a targeted product. However, searching for a product, collecting all the relevant information, and reaching a decision is a tedious task that needs to be automated. Such composed decision-assisting text data analysis systems are not conveniently available worldwide. Such systems are a dream for major cities of South Punjab, such as Bahawalpur, Multan, and Rahimyar khan. This scenario creates a gap that needs to be filled. In this work, the popularity of clothing brands in three cities of south Punjab has been assessed by analysing the brand's popularity using sentiment analysis by prioritizing brands based on organic feedback from their potential customers. This study uses a combination of quantitative and qualitative research to examine online reviews from Google Maps. The task is accomplished by applying machine learning techniques, Logistic Regression (LR), and Support Vector Machine (SVM), on Google Maps reviews data using the n-gram feature extraction approach. The SVM algorithm proved to be better than others with the uni-bi-trigram features extraction method, achieving an average of 80.93% accuracy.
- 13 January 2023
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- p. e10
Open AccessGoogle Maps Data Analysis of Clothing Brands in South Punjab, Pakistan
The Internet is a popular and first-hand source of data about products and services. Before buying a product, people try to gain quick insight by scanning through online reviews about a targeted product. However, searching for a product, collecting all the relevant information, and reaching a decision is a tedious task that needs to be automated. Such composed decision-assisting text data analysis systems are not conveniently available worldwide. Such systems are a dream for major cities of South Punjab, such as Bahawalpur, Multan, and Rahimyar khan. This scenario creates a gap that needs to be filled. In this work, the popularity of clothing brands in three cities of south Punjab has been assessed by analysing the brand's popularity using sentiment analysis by prioritizing brands based on organic feedback from their potential customers. This study uses a combination of quantitative and qualitative research to examine online reviews from Google Maps. The task is accomplished by applying machine learning techniques, Logistic Regression (LR), and Support Vector Machine (SVM), on Google Maps reviews data using the n-gram feature extraction approach. The SVM algorithm proved to be better than others with the uni-bi-trigram features extraction method, achieving an average of 80.93% accuracy.