Muhammad Abulaish
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Muhammad Abulaish has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
Sajid Yousuf Bhat
Department of Computer Science, University of Kashmir, Srinagar, Jammu and Kashmir, India
5 shared publicationsLipika Dey
4 shared publications- Amit Kumar Sah
Department of Computer Science, South Asian University, Maidan Garhi, New Delhi, India
3 shared publications Ashraf Kamal
Department of Computer Science, Jamia Millia Islamia (A Central University), New Delhi, India
3 shared publicationsJahiruddin
Department of Computer Science
3 shared publications- Mohd Fazil
College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia
3 shared publications
Latest Publications
- Open Access
- 19 March 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8  (3) , 79
RolEmo: A Role-Aware Commonsense-Augmented Contrastive Learning Framework for Emotion Classification
Emotion classification is a fundamental task in affective computing, with applications in human–computer interaction, mental health monitoring, and social media analysis. Although most existing methods formulate it as a flat classification problem, emotional expressions are inherently structured and grounded in semantic roles such as the emotion cue, stimulus, experiencer, and target. However, the relative contribution of these roles to emotion inference has not been systematically examined. Unlike prior models, we propose RolEmo, a role-aware framework for emotion classification that explicitly incorporates semantic role information. The framework employs a controlled role-masking strategy to analyze the contribution of individual roles, augments textual representations with external commonsense knowledge to capture implicit affective context, and applies supervised contrastive learning to structure the embedding space by bringing emotionally similar instances closer while separating opposing ones. We evaluate RolEmo on three benchmark datasets annotated with semantic roles. Experimental results demonstrate that RolEmo outperforms the strongest baseline across three datasets by up to , , and in the Full Text, Only Role, and Without Role settings, respectively. The analysis further indicates that the cue and stimulus roles provide the most reliable signals for emotion classification, with their removal causing performance drops of up to in macro f1-score, while experiencer and target roles exhibit more variable effects. These findings highlight the importance of structured semantic modeling and commonsense reasoning for robust and interpretable emotion understanding.- 19 March 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8  (3) , 79
Open AccessRolEmo: A Role-Aware Commonsense-Augmented Contrastive Learning Framework for Emotion Classification
Emotion classification is a fundamental task in affective computing, with applications in human–computer interaction, mental health monitoring, and social media analysis. Although most existing methods formulate it as a flat classification problem, emotional expressions are inherently structured and grounded in semantic roles such as the emotion cue, stimulus, experiencer, and target. However, the relative contribution of these roles to emotion inference has not been systematically examined. Unlike prior models, we propose RolEmo, a role-aware framework for emotion classification that explicitly incorporates semantic role information. The framework employs a controlled role-masking strategy to analyze the contribution of individual roles, augments textual representations with external commonsense knowledge to capture implicit affective context, and applies supervised contrastive learning to structure the embedding space by bringing emotionally similar instances closer while separating opposing ones. We evaluate RolEmo on three benchmark datasets annotated with semantic roles. Experimental results demonstrate that RolEmo outperforms the strongest baseline across three datasets by up to , , and in the Full Text, Only Role, and Without Role settings, respectively. The analysis further indicates that the cue and stimulus roles provide the most reliable signals for emotion classification, with their removal causing performance drops of up to in macro f1-score, while experiencer and target roles exhibit more variable effects. These findings highlight the importance of structured semantic modeling and commonsense reasoning for robust and interpretable emotion understanding. - Open Access
- 2 July 2025
- Published by Elsevier in Machine Learning with Applications
- Vol. 21
EmoFusion: An integrated machine learning model leveraging embeddings and lexicons to improve textual emotion classification
- 2 July 2025
- Published by Elsevier in Machine Learning with Applications
- Vol. 21
Open AccessEmoFusion: An integrated machine learning model leveraging embeddings and lexicons to improve textual emotion classification
- 1 June 2025
- Published by SAGE Publications in Big Data
- Vol. 13  (3) , 243-268
A MapReduce-Based Approach for Fast Connected Components Detection from Large-Scale Networks
Owing to increasing size of the real-world networks, their processing using classical techniques has become infeasible. The amount of storage and central processing unit time required for processing large networks is far beyond the capabilities of a high-end computing machine. Moreover, real-world network data are generally distributed in nature because they are collected and stored on distributed platforms. This has popularized the use of the MapReduce, a distributed data processing framework, for analyzing real-world network data. Existing MapReduce-based methods for connected components detection mainly struggle to minimize the number of MapReduce rounds and the amount of data generated and forwarded to the subsequent rounds. This article presents an efficient MapReduce-based approach for finding connected components, which does not forward the complete set of connected components to the subsequent rounds; instead, it writes them to the Hadoop Distributed File System as soon as they are found to reduce the amount of data forwarded to the subsequent rounds. It also presents an application of the proposed method in contact tracing. The proposed method is evaluated on several network data sets and compared with two state-of-the-art methods. The empirical results reveal that the proposed method performs significantly better and is scalable to find connected components in large-scale networks.
- 1 June 2025
- Published by SAGE Publications in Big Data
- Vol. 13  (3) , 243-268
A MapReduce-Based Approach for Fast Connected Components Detection from Large-Scale Networks
Owing to increasing size of the real-world networks, their processing using classical techniques has become infeasible. The amount of storage and central processing unit time required for processing large networks is far beyond the capabilities of a high-end computing machine. Moreover, real-world network data are generally distributed in nature because they are collected and stored on distributed platforms. This has popularized the use of the MapReduce, a distributed data processing framework, for analyzing real-world network data. Existing MapReduce-based methods for connected components detection mainly struggle to minimize the number of MapReduce rounds and the amount of data generated and forwarded to the subsequent rounds. This article presents an efficient MapReduce-based approach for finding connected components, which does not forward the complete set of connected components to the subsequent rounds; instead, it writes them to the Hadoop Distributed File System as soon as they are found to reduce the amount of data forwarded to the subsequent rounds. It also presents an application of the proposed method in contact tracing. The proposed method is evaluated on several network data sets and compared with two state-of-the-art methods. The empirical results reveal that the proposed method performs significantly better and is scalable to find connected components in large-scale networks.
- 10 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
CARES: A commonsense knowledge-enriched and graph-based contextual learning approach for rumor detection on social media
- 10 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
CARES: A commonsense knowledge-enriched and graph-based contextual learning approach for rumor detection on social media
- Open Access
- 30 November 2024
- Published by Walter de Gruyter GmbH in Foundations of Computing and Decision Sciences
- Vol. 49  (4) , 409-430
Leveraging Unseen Features along with their PLM-based Representation to Handle Negative Covariate Shift Problem in Text Classification
This paper presents a novel approach to address the problem of negative covariate shift by using unseen features. Covariate shift occurs when there is a drift between the data observed during the training and testing phase of a machine learning model. Covariate shift typically transpires in the negative class as a consequence of the swift evolution of topics discussed therein, which is driven by the characteristics of online social media. Because there is a shift in data, it signals that the data is changing, and it includes features that the trained model did not see during the training phase. We refer to such features as unseen features . To the best of our knowledge, we are the first to use unseen features to address negative covariate shift problem. The proposed approach is compared to three baselines and one state-of-theart method. The experimental results obtained from a multi-domain sentiment dataset show that the proposed approach outperforms the baselines and state-of-the-art approaches by a significant margin in terms of various performance evaluation metrics.
- 30 November 2024
- Published by Walter de Gruyter GmbH in Foundations of Computing and Decision Sciences
- Vol. 49  (4) , 409-430
Open AccessLeveraging Unseen Features along with their PLM-based Representation to Handle Negative Covariate Shift Problem in Text Classification
This paper presents a novel approach to address the problem of negative covariate shift by using unseen features. Covariate shift occurs when there is a drift between the data observed during the training and testing phase of a machine learning model. Covariate shift typically transpires in the negative class as a consequence of the swift evolution of topics discussed therein, which is driven by the characteristics of online social media. Because there is a shift in data, it signals that the data is changing, and it includes features that the trained model did not see during the training phase. We refer to such features as unseen features . To the best of our knowledge, we are the first to use unseen features to address negative covariate shift problem. The proposed approach is compared to three baselines and one state-of-theart method. The experimental results obtained from a multi-domain sentiment dataset show that the proposed approach outperforms the baselines and state-of-the-art approaches by a significant margin in terms of various performance evaluation metrics.
- 4 November 2024
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20  (4) , 3495-3512
Handling imbalanced textual data: an attention-based data augmentation approach
- 4 November 2024
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20  (4) , 3495-3512
Handling imbalanced textual data: an attention-based data augmentation approach
- Open Access
- 30 July 2024
- Published by Springer Nature in Research Square
DrSbChain: A Snowball-Chain Approach for Detecting Communities in Directed Social Graphs
This paper presents a heterogeneous technique for detecting communities from social graphs called as DrSbChain. It operates in two phases; wherein, it gathers local information from the graph and processes one node at a time (i.e., seed nodes) in the first phase. It employs simple topological properties of the graph to determine the best neighbors nodes for the seed nodes in the graph and merges them to build a chain, referred to as a snowball-chain inspired by the concept of snowball sampling. In each successive iteration, the chains identified in the previous iteration can be combined to form larger snowballs until all the nodes are covered. Finally, the algorithm’s initial phase yields local communities. The second phase merges the local communities using a merge criteria, resulting in the final set of communities. The novelty of DrSbChain is that it can work on both, directed and undirected social graphs, and detect overlapping as well as disjoint communities by just setting a binary parameter value. The overlapping communities produced by DrSbChain are evaluated using link modularity and overlapping normalized mutual information (ONMI) and compared with several state of the art methods. Based on the empirical results, DrSbChain is found to produce better results for link modularity and at par ONMI values. Also, disjoint communities are evaluated using another parameter called the newman modularity along with the previous two measures. This paper also describes an application of the proposed DrSbChain technique to identify communities based on user check-ins from the location-based social networking site Brightkite that can be prove to be useful for influential node identification.
- 30 July 2024
- Published by Springer Nature in Research Square
Open AccessDrSbChain: A Snowball-Chain Approach for Detecting Communities in Directed Social Graphs
This paper presents a heterogeneous technique for detecting communities from social graphs called as DrSbChain. It operates in two phases; wherein, it gathers local information from the graph and processes one node at a time (i.e., seed nodes) in the first phase. It employs simple topological properties of the graph to determine the best neighbors nodes for the seed nodes in the graph and merges them to build a chain, referred to as a snowball-chain inspired by the concept of snowball sampling. In each successive iteration, the chains identified in the previous iteration can be combined to form larger snowballs until all the nodes are covered. Finally, the algorithm’s initial phase yields local communities. The second phase merges the local communities using a merge criteria, resulting in the final set of communities. The novelty of DrSbChain is that it can work on both, directed and undirected social graphs, and detect overlapping as well as disjoint communities by just setting a binary parameter value. The overlapping communities produced by DrSbChain are evaluated using link modularity and overlapping normalized mutual information (ONMI) and compared with several state of the art methods. Based on the empirical results, DrSbChain is found to produce better results for link modularity and at par ONMI values. Also, disjoint communities are evaluated using another parameter called the newman modularity along with the previous two measures. This paper also describes an application of the proposed DrSbChain technique to identify communities based on user check-ins from the location-based social networking site Brightkite that can be prove to be useful for influential node identification.
- Open Access
- 14 July 2024
- Published by Elsevier in Machine Learning with Applications
- Vol. 17
DeepCKID: A Multi-Head Attention-Based Deep Neural Network Model Leveraging Classwise Knowledge to Handle Imbalanced Textual Data
- 14 July 2024
- Published by Elsevier in Machine Learning with Applications
- Vol. 17
Open AccessDeepCKID: A Multi-Head Attention-Based Deep Neural Network Model Leveraging Classwise Knowledge to Handle Imbalanced Textual Data
- 29 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11  (4) , 5483-5495
conteNXt: A Graph-Based Approach to Assimilate Content and Context for Event Detection in OSN
Social networks are rapidly expanding due to their imperative role in disseminating information in a split second, emerging as the primary source for breaking news. As a result, the rich, user-generated information entices researchers to delve deeper and extract valuable insights. Event detection in online social networks (OSNs) is a research problem that has shifted researchers attention from traditional news media to online social media data. Event detection in OSNs is an automated process, addressing the impractical task of manually filtering potential events from vast amounts of online data. Unfortunately, the informality and semantic sparsity of online social networking text pose significant challenges to the event detection task. To this end, we present an approach named conteNXt for detecting events from Twitter (currently “X”) posts (also known as Tweets). To handle large amounts of data, the proposed method divides tweets into bins and uses postprocessing methods to extract bursty keyphrases. These keyphrases are then used to generate a weighted keyphrase graph using the Word2Vec model. Finally, Markov clustering is employed to cluster and detect events in the bursty keyphrase graph. conteNXt is evaluated on the Event-Corpus2012 benchmark dataset and two additional datasets extracted from the archive, Archive2020 and Archive2021 , using performance evaluation metrics: #events, precision, recall, and F1-score. The proposed approach outperforms state-of-the-art methods, including SEDTWik , Twevent , Sentence-BERT , MABED , EDED , CommunityINDICATOR , and EventX . Additionally, the proposed approach is capable of detecting vital events that are not identified by the aforementioned state-of-the-art methods.
- 29 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11  (4) , 5483-5495
conteNXt: A Graph-Based Approach to Assimilate Content and Context for Event Detection in OSN
Social networks are rapidly expanding due to their imperative role in disseminating information in a split second, emerging as the primary source for breaking news. As a result, the rich, user-generated information entices researchers to delve deeper and extract valuable insights. Event detection in online social networks (OSNs) is a research problem that has shifted researchers attention from traditional news media to online social media data. Event detection in OSNs is an automated process, addressing the impractical task of manually filtering potential events from vast amounts of online data. Unfortunately, the informality and semantic sparsity of online social networking text pose significant challenges to the event detection task. To this end, we present an approach named conteNXt for detecting events from Twitter (currently “X”) posts (also known as Tweets). To handle large amounts of data, the proposed method divides tweets into bins and uses postprocessing methods to extract bursty keyphrases. These keyphrases are then used to generate a weighted keyphrase graph using the Word2Vec model. Finally, Markov clustering is employed to cluster and detect events in the bursty keyphrase graph. conteNXt is evaluated on the Event-Corpus2012 benchmark dataset and two additional datasets extracted from the archive, Archive2020 and Archive2021 , using performance evaluation metrics: #events, precision, recall, and F1-score. The proposed approach outperforms state-of-the-art methods, including SEDTWik , Twevent , Sentence-BERT , MABED , EDED , CommunityINDICATOR , and EventX . Additionally, the proposed approach is capable of detecting vital events that are not identified by the aforementioned state-of-the-art methods.
- Open Access
- 27 March 2024
- Published by River Publishers in Journal of Web Engineering
- Vol. 23  (1) , 27-52
Contextualized Satire Detection in Short Texts Using Deep Learning Techniques
Satire is prominent in user-generated content on various online platforms in the form of satirical news, customer reviews, blogs, articles, and short messages that are typically of an informal nature. As satire is also used to disseminate false information on the Internet, its computational detection has become a well-known issue. Existing work focuses primarily on formal document- or sentence-level textual data, whereas informal short texts have gotten less attention for satire detection. This paper presents a new model called BiLSTM self-attention (BiSAT) for detecting satire in informal short texts. It consists of various components such as input, embedding, self-attention, and two bi-directional long short-term memory (BiLSTM) layers for learning crucial contextual information pertaining to the satire present in the texts. The input layer uses the text as input to create an input vector, which is then given to the embedding layer to create the appropriate numeric vector. The output of the embedding layer is passed on to the first BiLSTM layer, which extracts contextual information-based sequences in the opposite direction. Between the first and second BiLSTM layers, a self-attention layer is employed to draw attention to the important satirical information that is acquired by the hidden layer of the first BiLSTM. The BiSAT model also takes a classic feature engineering approach, employing a 13-dimensional auxiliary feature vector comprised of features from four separate feature categories: sentiment, punctuation, hyperbole, and affective. The proposed BiSAT model is empirically evaluated on two benchmark datasets and a newly created dataset called Satire-280. It outperforms existing research and baseline methods by a significant margin. The Satire-280 dataset along with code can be downloaded from GitHub repository: https://github.com/Ashraf-Kamal/Satire-Detection.
- 27 March 2024
- Published by River Publishers in Journal of Web Engineering
- Vol. 23  (1) , 27-52
Open AccessContextualized Satire Detection in Short Texts Using Deep Learning Techniques
Satire is prominent in user-generated content on various online platforms in the form of satirical news, customer reviews, blogs, articles, and short messages that are typically of an informal nature. As satire is also used to disseminate false information on the Internet, its computational detection has become a well-known issue. Existing work focuses primarily on formal document- or sentence-level textual data, whereas informal short texts have gotten less attention for satire detection. This paper presents a new model called BiLSTM self-attention (BiSAT) for detecting satire in informal short texts. It consists of various components such as input, embedding, self-attention, and two bi-directional long short-term memory (BiLSTM) layers for learning crucial contextual information pertaining to the satire present in the texts. The input layer uses the text as input to create an input vector, which is then given to the embedding layer to create the appropriate numeric vector. The output of the embedding layer is passed on to the first BiLSTM layer, which extracts contextual information-based sequences in the opposite direction. Between the first and second BiLSTM layers, a self-attention layer is employed to draw attention to the important satirical information that is acquired by the hidden layer of the first BiLSTM. The BiSAT model also takes a classic feature engineering approach, employing a 13-dimensional auxiliary feature vector comprised of features from four separate feature categories: sentiment, punctuation, hyperbole, and affective. The proposed BiSAT model is empirically evaluated on two benchmark datasets and a newly created dataset called Satire-280. It outperforms existing research and baseline methods by a significant margin. The Satire-280 dataset along with code can be downloaded from GitHub repository: https://github.com/Ashraf-Kamal/Satire-Detection.