Muhammad Yaseen Khan
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 Yaseen Khan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Shaukat Wasi
Department of Computer Science, Muhammad Ali Jinnah University, Karachi, Pakistan
4 shared publications - Muhammad Shoaib Siddiqui
Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia
2 shared publications - Muhammad Suffian
DICEAM, Mediterranea University of Reggio Calabria
2 shared publications - Tafseer Ahmed
Center for Language Computing, Mohammad Ali Jinnah University, Karachi, Pakistan
2 shared publications - Abdul Qayoom
Center for Language Computing, Mohammad Ali Jinnah University, Karachi 75400, Pakistan
1 shared publication Aisha Nazir
1 shared publication
Latest Publications
- Open Access
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 126661-126690
Cognitive Relationship-Based Approach for Urdu Sarcasm and Sentiment Classification
Humans have a natural tendency to express their emotions, but they are also skilled at using sarcasm to shape their feelings. In cognitive computing and natural language processing research, sentiment analysis and sarcasm detection are typically treated as separate tasks, with each text analyzed in isolation. However, this approach overlooks the connection between sentiment and sarcasm. We believe that sentiment and sarcasm are closely related and should be analyzed together to achieve a better understanding of context and natural language. In this paper, we propose a new framework that leverages the Cognitive Relationship (CR) between sarcasm and sentiment to improve the accuracy of classification. By taking into account the relationship between these two factors, we can achieve better results in sentiment analysis and sarcasm detection. We have also created a new and nearly balanced dataset for sentiment and sarcasm classification in standard Urdu that contains 7,000 tweets, which make up over 210K tokens. To gain a better understanding of the data, we conducted exploratory data analysis on words, hashtags, and emojis. The proposed methodology conducted a variety of classical machine learning classifiers and tested them with different variations of the dataset. After a thorough analysis of the results and errors, we found that the CR-based approach for sarcasm and sentiment classification performed better than the traditional stand-alone (SA) approach. Among the classifiers, Linear Regression and eXtreme Gradient Boosting proved to be the most effective. The sentiment classification based on CR has demonstrated a 9.3% enhancement compared to the stand-alone (SA) method while maintaining an overall improvement of approximately 22% compared to the baseline distribution. In the same way, the sarcasm classification based on CR has shown a 9.1% improvement over the SA approach and approximately 23.6% improvement over the baseline distribution.
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 126661-126690
Open AccessCognitive Relationship-Based Approach for Urdu Sarcasm and Sentiment Classification
Humans have a natural tendency to express their emotions, but they are also skilled at using sarcasm to shape their feelings. In cognitive computing and natural language processing research, sentiment analysis and sarcasm detection are typically treated as separate tasks, with each text analyzed in isolation. However, this approach overlooks the connection between sentiment and sarcasm. We believe that sentiment and sarcasm are closely related and should be analyzed together to achieve a better understanding of context and natural language. In this paper, we propose a new framework that leverages the Cognitive Relationship (CR) between sarcasm and sentiment to improve the accuracy of classification. By taking into account the relationship between these two factors, we can achieve better results in sentiment analysis and sarcasm detection. We have also created a new and nearly balanced dataset for sentiment and sarcasm classification in standard Urdu that contains 7,000 tweets, which make up over 210K tokens. To gain a better understanding of the data, we conducted exploratory data analysis on words, hashtags, and emojis. The proposed methodology conducted a variety of classical machine learning classifiers and tested them with different variations of the dataset. After a thorough analysis of the results and errors, we found that the CR-based approach for sarcasm and sentiment classification performed better than the traditional stand-alone (SA) approach. Among the classifiers, Linear Regression and eXtreme Gradient Boosting proved to be the most effective. The sentiment classification based on CR has demonstrated a 9.3% enhancement compared to the stand-alone (SA) method while maintaining an overall improvement of approximately 22% compared to the baseline distribution. In the same way, the sarcasm classification based on CR has shown a 9.1% improvement over the SA approach and approximately 23.6% improvement over the baseline distribution.
- Open Access
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 1533-1544
Discovering Lexical Similarity Using Articulatory Feature-Based Phonetic Edit Distance
Lexical Similarity (LS) between two languages uncovers many interesting linguistic insights such as phylogenetic relationship, mutual intelligibility, common etymology, and loan words. There are various methods through which LS is evaluated. This paper presents a method of Phonetic Edit Distance (PED) that uses a soft comparison of letters using the articulatory features associated with their International Phonetic Alphabet (IPA) transcription. In particular, the comparison between the articulatory features of two letters taken from words belonging to different languages is used to compute the cost of replacement in the inner loop of edit distance computation. As an example, PED gives edit distance of 0.82 between German word ‘vater’ ([fa:tər]) and Persian word ‘ ’ ([pedær]), meaning ‘father,’ and, similarly, PED of 0.93 between Hebrew word ‘ ’ ([ʃəɭam]) and Arabic word ‘ ’ ([səɭa:m], meaning ‘peace,’ whereas classical edit distances would be 4 and 2, respectively. We report the results of systematic experiments conducted on six languages: Arabic, Hindi, Marathi, Persian, Sanskrit, and Urdu. Universal Dependencies (UD) corpora were used to restrict the comparison to lists of words belonging to the same part of speech. The LS based on the average PED between pair of words was then computed for each pair of languages, unveiling similarities otherwise masked by the adoption of different alphabets, grammars, and pronunciations rules.
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 1533-1544
Open AccessDiscovering Lexical Similarity Using Articulatory Feature-Based Phonetic Edit Distance
Lexical Similarity (LS) between two languages uncovers many interesting linguistic insights such as phylogenetic relationship, mutual intelligibility, common etymology, and loan words. There are various methods through which LS is evaluated. This paper presents a method of Phonetic Edit Distance (PED) that uses a soft comparison of letters using the articulatory features associated with their International Phonetic Alphabet (IPA) transcription. In particular, the comparison between the articulatory features of two letters taken from words belonging to different languages is used to compute the cost of replacement in the inner loop of edit distance computation. As an example, PED gives edit distance of 0.82 between German word ‘vater’ ([fa:tər]) and Persian word ‘ ’ ([pedær]), meaning ‘father,’ and, similarly, PED of 0.93 between Hebrew word ‘ ’ ([ʃəɭam]) and Arabic word ‘ ’ ([səɭa:m], meaning ‘peace,’ whereas classical edit distances would be 4 and 2, respectively. We report the results of systematic experiments conducted on six languages: Arabic, Hindi, Marathi, Persian, Sanskrit, and Urdu. Universal Dependencies (UD) corpora were used to restrict the comparison to lists of words belonging to the same part of speech. The LS based on the average PED between pair of words was then computed for each pair of languages, unveiling similarities otherwise masked by the adoption of different alphabets, grammars, and pronunciations rules.
- Open Access
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Automated Prediction of Good Dictionary EXamples (GDEX): A Comprehensive Experiment with Distant Supervision, Machine Learning, and Word Embedding‐Based Deep Learning Techniques
Dictionaries not only are the source of getting meanings of the word but also serve the purpose of comprehending the context in which the words are used. For such purpose, we see a small sentence as an example for the very word in comprehensive book‐dictionaries and more recently in online dictionaries. The lexicographers perform a very meticulous activity for the elicitation of Good Dictionary EXamples (GDEX)—a sentence that is best fit in a dictionary for the word’s definition. The rules for the elicitation of GDEX are very strenuous and require a lot of time for committing the manual process. In this regard, this paper focuses on two major tasks, i.e., the development of labelled corpora for top 3K English words through the usage of distant supervision approach and devising a state‐of‐the‐art artificial intelligence‐based automated procedure for discriminating Good Dictionary EXamples from the bad ones. The proposed methodology involves a suite of five machine learning (ML) and five word embedding‐based deep learning (DL) architectures. A thorough analysis of the results shows that GDEX elicitation can be done by both ML and DL models; however, DL‐based models show a trivial improvement of 3.5% over the conventional ML models. We find that the random forests with parts‐of‐speech information and word2vec‐based bidirectional LSTM are the most optimal ML and DL combinations for automated GDEX elicitation; on the test set, these models, respectively, secured a balanced accuracy of 73% and 77%.
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Open AccessAutomated Prediction of Good Dictionary EXamples (GDEX): A Comprehensive Experiment with Distant Supervision, Machine Learning, and Word Embedding‐Based Deep Learning Techniques
Dictionaries not only are the source of getting meanings of the word but also serve the purpose of comprehending the context in which the words are used. For such purpose, we see a small sentence as an example for the very word in comprehensive book‐dictionaries and more recently in online dictionaries. The lexicographers perform a very meticulous activity for the elicitation of Good Dictionary EXamples (GDEX)—a sentence that is best fit in a dictionary for the word’s definition. The rules for the elicitation of GDEX are very strenuous and require a lot of time for committing the manual process. In this regard, this paper focuses on two major tasks, i.e., the development of labelled corpora for top 3K English words through the usage of distant supervision approach and devising a state‐of‐the‐art artificial intelligence‐based automated procedure for discriminating Good Dictionary EXamples from the bad ones. The proposed methodology involves a suite of five machine learning (ML) and five word embedding‐based deep learning (DL) architectures. A thorough analysis of the results shows that GDEX elicitation can be done by both ML and DL models; however, DL‐based models show a trivial improvement of 3.5% over the conventional ML models. We find that the random forests with parts‐of‐speech information and word2vec‐based bidirectional LSTM are the most optimal ML and DL combinations for automated GDEX elicitation; on the test set, these models, respectively, secured a balanced accuracy of 73% and 77%.
- Open Access
- 1 January 2019
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 10 (9)
A Novel Approach for Ontology-Driven Information Retrieving Chatbot for Fashion Brands
Chatbots or conversational agents are the most projecting and widely employed artificial assistants on online social media. These bots converse with the humans in audio, visual, or textual formats. It is quite intelligible that users are keen interested in the swift and relatedly correct information for their hunt in pursuit of desired product, such that their precious time is not wasted through surfing multiple websites and business portals. In this paper, we present a novel incremental approach for building a chatbot for fashion brands based on the semantic web. We organized a dataset of 5,000 question and answers of top- 10 brands in the fashion domain, which covers the information about new arrivals, sales, packages, discounts, exchange/return policies, etc. We have also developed a dialogue interface for querying the system. The results generated against the queries are thoroughly evaluated on the criteria of time, context, history, duration, turns, significance, relevance, and fall back questions.
- 1 January 2019
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 10 (9)
Open AccessA Novel Approach for Ontology-Driven Information Retrieving Chatbot for Fashion Brands
Chatbots or conversational agents are the most projecting and widely employed artificial assistants on online social media. These bots converse with the humans in audio, visual, or textual formats. It is quite intelligible that users are keen interested in the swift and relatedly correct information for their hunt in pursuit of desired product, such that their precious time is not wasted through surfing multiple websites and business portals. In this paper, we present a novel incremental approach for building a chatbot for fashion brands based on the semantic web. We organized a dataset of 5,000 question and answers of top- 10 brands in the fashion domain, which covers the information about new arrivals, sales, packages, discounts, exchange/return policies, etc. We have also developed a dialogue interface for querying the system. The results generated against the queries are thoroughly evaluated on the criteria of time, context, history, duration, turns, significance, relevance, and fall back questions.
- Open Access
- 1 January 2018
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 9 (9)
Developing Disease Classification System based on Keyword Extraction and Supervised Learning
The Evidence-Based Medicine (EBM) is emerged as the helpful practice for medical practitioners to make decisions with available shreds of evidence along with their professional ex-pertise. In EBM, the medical practitioners suggest the medication on the basis of underlying information of patients descriptions and medical records (mostly available in textual form). This paper presents a novel and efficient method for predicting the correct disease. Since these type of tasks are generally accounted as the multi-class classifying problem, therefore, a large number of records are needed, so a large number of records will be entertained in higher n-dimensional space. Our system, as proposed in this paper, will utilise the key-phrases extraction techniques to scoop out the meaningful information to reduce the size of textual dimension, and, the suite of machine learning algorithms for classifying the diseases efficiently. We have tested the proposed approach on 6 different diseases i.e. Asthma, Hypertension, Diabetes, Fever, Abdominal issues, and Heart problems over the dataset of 690 patients. With key-phrases tested in the range [3,7] features, SVM has shown the highest (93.34%, 95%) F1-score and accuracy.
- 1 January 2018
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 9 (9)
Open AccessDeveloping Disease Classification System based on Keyword Extraction and Supervised Learning
The Evidence-Based Medicine (EBM) is emerged as the helpful practice for medical practitioners to make decisions with available shreds of evidence along with their professional ex-pertise. In EBM, the medical practitioners suggest the medication on the basis of underlying information of patients descriptions and medical records (mostly available in textual form). This paper presents a novel and efficient method for predicting the correct disease. Since these type of tasks are generally accounted as the multi-class classifying problem, therefore, a large number of records are needed, so a large number of records will be entertained in higher n-dimensional space. Our system, as proposed in this paper, will utilise the key-phrases extraction techniques to scoop out the meaningful information to reduce the size of textual dimension, and, the suite of machine learning algorithms for classifying the diseases efficiently. We have tested the proposed approach on 6 different diseases i.e. Asthma, Hypertension, Diabetes, Fever, Abdominal issues, and Heart problems over the dataset of 690 patients. With key-phrases tested in the range [3,7] features, SVM has shown the highest (93.34%, 95%) F1-score and accuracy.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Drive pattern analyzer using smartphones
This paper is about analyzing the efficiency of drivers using an android based smartphone. Smartphones have built-in sensors for instance: accelerometer, gyroscope etc. Utilizing these sensors will provide day-end analysis to track the driving behaviour and provide feedback to the drivers if there is any inappropriate or reckless action taken while driving. To summarize this, we propose to build an active and accurate monitoring system that gives the response to the driving behaviours of a driver.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Drive pattern analyzer using smartphones
This paper is about analyzing the efficiency of drivers using an android based smartphone. Smartphones have built-in sensors for instance: accelerometer, gyroscope etc. Utilizing these sensors will provide day-end analysis to track the driving behaviour and provide feedback to the drivers if there is any inappropriate or reckless action taken while driving. To summarize this, we propose to build an active and accurate monitoring system that gives the response to the driving behaviours of a driver.
- 1 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 242-249
Harnessing English Sentiment Lexicons for Polarity Detection in Urdu Tweets: A Baseline Approach
It is human instinct to express emotions, and with increasing use of social media, it is more often being expressed through text messages than ever before. The emotions and sentiments encoded in these short text messages are of keen interest to various marketing and advertising agencies. Thus, various lexicons and algorithms have been devised for English, and French language to extract these hidden sentiments. On the other hand, Urdu (or Hindi) the third widely-spoken language in the world [1], lacks any such sentiment lexicons or algorithms. Instead of starting from scratch, we make use of the existing English sentiment lexicons to develop the first sentiment lexicon for Urdu. This lexicon will serve as a baseline for future lexicons developed through more intimate knowledge of Urdu language. Furthermore, we compare its performance with various machine learning (ML) approaches. We also make public the labeled dataset developed by us for Urdu sentiment analysis. We hope that this lexicon and dataset will serve as a benchmark for evaluation of future lexicons and ML approaches for the Urdu language.
- 1 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 242-249
Harnessing English Sentiment Lexicons for Polarity Detection in Urdu Tweets: A Baseline Approach
It is human instinct to express emotions, and with increasing use of social media, it is more often being expressed through text messages than ever before. The emotions and sentiments encoded in these short text messages are of keen interest to various marketing and advertising agencies. Thus, various lexicons and algorithms have been devised for English, and French language to extract these hidden sentiments. On the other hand, Urdu (or Hindi) the third widely-spoken language in the world [1], lacks any such sentiment lexicons or algorithms. Instead of starting from scratch, we make use of the existing English sentiment lexicons to develop the first sentiment lexicon for Urdu. This lexicon will serve as a baseline for future lexicons developed through more intimate knowledge of Urdu language. Furthermore, we compare its performance with various machine learning (ML) approaches. We also make public the labeled dataset developed by us for Urdu sentiment analysis. We hope that this lexicon and dataset will serve as a benchmark for evaluation of future lexicons and ML approaches for the Urdu language.