Tehmina Amjad | International Islamic University Islamabad (original) (raw)
Papers by Tehmina Amjad
IEEE Transactions on Computational Social Systems
Journal of Engineering and Applied Sciences , University of Engineering and Technology, Peshawar, 2016
Existing indexing methods do not consider the variation among number of citations received by pub... more Existing indexing methods do not consider the variation among number of citations received by publications of authors. In this paper, we propose variation in citation based fractional index which not only consider the number of authors but also the variation factor in the number of citations. Index considers the consistency in received citations of publication in addition to their quality and quantity for indexing. We have used Co-efficient of quartile deviation for calculation of variation in received citations because it is sensitive for both skewed and un-skewed data. We have used real world data for validation purpose and have used fractional h- and g-index as our baseline indexing methods. We compared the results of our proposed method with baseline methods and have analyzed that our intuition has clear impact on the authors indexing. Author on higher index in fractional index gets impacted by -index and its rank changes accordingly. Baseline methods do not considers variati...
International Journal of Innovative Technology and Exploring Engineering, 2019
Named Entity Recognition (NER) is a significant errand in Natural Language Processing (NLP) appli... more Named Entity Recognition (NER) is a significant errand in Natural Language Processing (NLP) applications like Information Extraction, Question Answering and so on. In this paper, factual way to deal with perceive Kannada named substances like individual name, area name, association name, number, estimation and time is proposed. We have achieved higher accuracy in CRF approach than the in HMM approach. The accuracy of classification is more accurate in CRF approach due to flexibility of adding more features unlike joint probability alone as in HMM. In HMM it is not practical to represent multiple overlapping features and long term dependencies. CRF ++ Tool Kit is used for experimentation. The consequences of acknowledgment are empowering and the approach has the exactness around 86%.
Journal of Alloys and Compounds, 2019
2021 International Conference on Artificial Intelligence (ICAI), 2021
In today’s interdisciplinary research society where researchers are interested to participate in ... more In today’s interdisciplinary research society where researchers are interested to participate in more than one discipline and they collaborate across disciplines, it is essential to understand the domain-specific impact of scholars. This study explores the impact of scholars who work in multiple disciplines and predicts scientific impact using multiple features. A Miner dataset is selected as a testbed and 10 sub-domains of computer science are analyzed. Despite today’s cross-discipline collaboration trend, there is a high number of scholars who work in a single domain as compared to those who work in multiple domains. Results show that among the 10 disciplines of computer science, “Network Control” gained high impact in terms of received citations. Various features are used to predict the future impact and “total papers” yield the highest R2 value followed by “topic-based citations” and “total citations”.
2018 14th International Conference on Emerging Technologies (ICET), 2018
Finding the rising stars is an interesting problem and has been recently studied in various domai... more Finding the rising stars is an interesting problem and has been recently studied in various domains including academic networks. This study formulates the problem of rising stars prediction as a machine learning task. Classification models are applied and features are classified as co-authors, author, and venues. The impact of the categorization of these features is empirically analyzed. The experimentation is performed on data of Pakistani researchers retrieved from Web of Sciences ranging from 2008 to 2014. After collection of the dataset, feature sets are calculated and classification techniques are applied. The researchers predicted by the proposed method are compared with top researchers of Pakistan in 2016 and 2017. The proposed technique solves the problem of finding rising star researcher of Pakistan in the field of computer sciences based on authors’ contribution, mutual influence, and venue citations scores.
2018 14th International Conference on Emerging Technologies (ICET), 2018
Identifying research areas of academicians is a challenging task. Most of the researchers have us... more Identifying research areas of academicians is a challenging task. Most of the researchers have used supervised machine learning to handle this task which requires labelled data. In this paper, we propose to use clique percolation (an overlapping community detection algorithm) to identify research areas of academicians. We propose a framework to collect data from digital libraries and websites of selected universities in Pakistan. We then identify researchers working in multiple research areas using clique percolation and present results of our analyses.
Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion, 2017
kuwait journal of science, 2016
Online bibliographic databases are providing significant resources to conduct analysis of academi... more Online bibliographic databases are providing significant resources to conduct analysis of academic social networks.We believe that work of an author is always influenced by work of his or her co-authors. In this study, we investigatethe impact of productivity and quality of work of an author’s co-authors on his or her ranking along with his owncontribution. We propose mutual influence (MI) based ranking method, which ranks authors based on (1) Publicationsof an author, along with impact of publications of his or her co-authors, (2) Normalized author position based Citationsweight, which is calculated from the citations received by an author with respect to position of his or her name in theco-authors list, (3) MINCC that combines the impact of both factors. A series of experiments has been conducted andresults show that proposed approach has capability to ranks authors in a significant way.
COVID-19 emerged in Wuhan and is later declared as a pandemic by World Health Organization. Diffe... more COVID-19 emerged in Wuhan and is later declared as a pandemic by World Health Organization. Different-aged people have varying gender-wise immunity control properties that necessitates understanding COVID-19 impact on age and gender which does not exist, currently. In this paper, COVID-19 surveillance variables are extensively studied along with hospitalization, tests-performed, and recovery data. Dataset is curated from three sources; however, age and gender data belong to Belgium, particularly. Visualizations, frequencies, Pearson’s and polyserial correlation, student’s t-test, and Cramer’s V are used for enhanced analysis. Results show higher mortality rate in males and need of more ventilators to combat severe symptoms.
kuwait journal of science, 2016
Machine learning and Statistical techniques are powerful analysis tools yet to be incorporated in... more Machine learning and Statistical techniques are powerful analysis tools yet to be incorporated in the new multidisciplinary field diversely termed as natural language processing (NLP) or computational linguistic. The linguistic knowledge may be ambiguous or contains ambiguity; therefore, various NLP tasks are carried out in order to resolve the ambiguity in speech and language processing.The current prevailing techniques for addressing various NLP tasks as a supervised learning are hidden Markov models (HMM), conditional random field (CRF), maximum entropy models (MaxEnt), support vector machines (SVM), Naive Bays, and deep learning (DL).The goal of this survey paper is to highlight ambiguity in speech and language processing, to provide brief overview of basic categories of linguistic knowledge, to discuss different existing machine learning models and their classification into different categories and finally to provide a comprehensive review of different state of the art machine ...
Library Hi Tech, 2021
Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scie... more Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scientific research. However, citation advantage varies from discipline to discipline, subject to subject and topic to topic. This study aims to compare the citation advantage of open access and toll access articles from four subfields of computer science. Design/methodology/approach This research studies the articles published by two prestigious publishers: Springer and Elsevier in the author-pays charges model from 2011 to 2015. For experimentation, four sub-domains of computer science are selected including (a) artificial intelligence, (b) human–computer interaction, (c) computer vision and graphics, and (d) software engineering. The open-access and toll-based citation advantage is studied and analyzed at the micro level within the computer science domain by performing independent sample t-tests. Findings The results of the study highlight that open access articles have a higher citation ...
Library Hi Tech, 2021
Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scie... more Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scientific research. However, citation advantage varies from discipline to discipline, subject to subject and topic to topic. This study aims to compare the citation advantage of open access and toll access articles from four subfields of computer science. Design/methodology/approach This research studies the articles published by two prestigious publishers: Springer and Elsevier in the author-pays charges model from 2011 to 2015. For experimentation, four sub-domains of computer science are selected including (a) artificial intelligence, (b) human–computer interaction, (c) computer vision and graphics, and (d) software engineering. The open-access and toll-based citation advantage is studied and analyzed at the micro level within the computer science domain by performing independent sample t-tests. Findings The results of the study highlight that open access articles have a higher citation ...
Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018
Players are ranked in various sports to show their importance over other players. Existing method... more Players are ranked in various sports to show their importance over other players. Existing methods only consider intra-type links (e.g., player to player and team to team), but ignore inter-type links (e.g., one type of player to another type of player, such as batsman to bowler and player to team) based on cognitive aspects. They also ignore the spatiality of the players. There is a strong relationship among players and their teams, which can be represented as a network consisting of multi-type interrelated objects. In this paper, we propose a players' ranking method, called Region-wise Players Link Fusion (RPLF) which is applied to the sport of cricket. RPLF considers players' region-wise intra-type and inter-type relation-based features to rank the players. Considering multi-type interrelated objects is based on the intuition that a batsman scoring high against top bowlers of a strong team or a bowler taking wickets against top batsmen of a strong team is considered as a good player. The experimental results show that RPLF provides promising insights of players' rankings. RLFP is a generic method and can be applied to different sports for ranking players.
COVID-19 has created anxiety not only in individuals but also in health organizations, and countr... more COVID-19 has created anxiety not only in individuals but also in health organizations, and countries worldwide. Not a single industry is left un-influenced and loss is being estimated in billions of dollars. The widespread of this pandemic disease has challenged researchers all over the world. Some of the researchers are working to invent its cure while, others are applying computing technologies to stop its spread, by analyzing and identifying patterns for prediction and forecasting. This is by no doubt the hottest area of research for the last 100 years. This survey has targeted the research published in computing sub-domains to combat the pandemic. The survey has clustered the scientific efforts into logical groups: surveillance, metrological effects, social media analytics, image processing and business and economy, analysis and modeling. It will serve as a leading source for the followings: researchers who want to identify what has been achieved in different computing sub-domai...
Entity resolution is a challenging and hot research area in the field of Information Systems sinc... more Entity resolution is a challenging and hot research area in the field of Information Systems since last decade. Author Name Disambiguation (AND) in Bibliographic Databases (BD) like DBLP , Citeseer , and Scopus is a specialized field of entity resolution. Given many citations of underlying authors, the AND task is to find which citations belong to the same author. In this survey, we start with three basic AND problems, followed by need for solution and challenges. A generic, five-step framework is provided for handling AND issues. These steps are; (1) Preparation of dataset (2) Selection of publication attributes (3) Selection of similarity metrics (4) Selection of models and (5) Clustering Performance evaluation. Categorization and elaboration of similarity metrics and methods are also provided. Finally, future directions and recommendations are given for this dynamic area of research.
IEEE Transactions on Computational Social Systems
Journal of Engineering and Applied Sciences , University of Engineering and Technology, Peshawar, 2016
Existing indexing methods do not consider the variation among number of citations received by pub... more Existing indexing methods do not consider the variation among number of citations received by publications of authors. In this paper, we propose variation in citation based fractional index which not only consider the number of authors but also the variation factor in the number of citations. Index considers the consistency in received citations of publication in addition to their quality and quantity for indexing. We have used Co-efficient of quartile deviation for calculation of variation in received citations because it is sensitive for both skewed and un-skewed data. We have used real world data for validation purpose and have used fractional h- and g-index as our baseline indexing methods. We compared the results of our proposed method with baseline methods and have analyzed that our intuition has clear impact on the authors indexing. Author on higher index in fractional index gets impacted by -index and its rank changes accordingly. Baseline methods do not considers variati...
International Journal of Innovative Technology and Exploring Engineering, 2019
Named Entity Recognition (NER) is a significant errand in Natural Language Processing (NLP) appli... more Named Entity Recognition (NER) is a significant errand in Natural Language Processing (NLP) applications like Information Extraction, Question Answering and so on. In this paper, factual way to deal with perceive Kannada named substances like individual name, area name, association name, number, estimation and time is proposed. We have achieved higher accuracy in CRF approach than the in HMM approach. The accuracy of classification is more accurate in CRF approach due to flexibility of adding more features unlike joint probability alone as in HMM. In HMM it is not practical to represent multiple overlapping features and long term dependencies. CRF ++ Tool Kit is used for experimentation. The consequences of acknowledgment are empowering and the approach has the exactness around 86%.
Journal of Alloys and Compounds, 2019
2021 International Conference on Artificial Intelligence (ICAI), 2021
In today’s interdisciplinary research society where researchers are interested to participate in ... more In today’s interdisciplinary research society where researchers are interested to participate in more than one discipline and they collaborate across disciplines, it is essential to understand the domain-specific impact of scholars. This study explores the impact of scholars who work in multiple disciplines and predicts scientific impact using multiple features. A Miner dataset is selected as a testbed and 10 sub-domains of computer science are analyzed. Despite today’s cross-discipline collaboration trend, there is a high number of scholars who work in a single domain as compared to those who work in multiple domains. Results show that among the 10 disciplines of computer science, “Network Control” gained high impact in terms of received citations. Various features are used to predict the future impact and “total papers” yield the highest R2 value followed by “topic-based citations” and “total citations”.
2018 14th International Conference on Emerging Technologies (ICET), 2018
Finding the rising stars is an interesting problem and has been recently studied in various domai... more Finding the rising stars is an interesting problem and has been recently studied in various domains including academic networks. This study formulates the problem of rising stars prediction as a machine learning task. Classification models are applied and features are classified as co-authors, author, and venues. The impact of the categorization of these features is empirically analyzed. The experimentation is performed on data of Pakistani researchers retrieved from Web of Sciences ranging from 2008 to 2014. After collection of the dataset, feature sets are calculated and classification techniques are applied. The researchers predicted by the proposed method are compared with top researchers of Pakistan in 2016 and 2017. The proposed technique solves the problem of finding rising star researcher of Pakistan in the field of computer sciences based on authors’ contribution, mutual influence, and venue citations scores.
2018 14th International Conference on Emerging Technologies (ICET), 2018
Identifying research areas of academicians is a challenging task. Most of the researchers have us... more Identifying research areas of academicians is a challenging task. Most of the researchers have used supervised machine learning to handle this task which requires labelled data. In this paper, we propose to use clique percolation (an overlapping community detection algorithm) to identify research areas of academicians. We propose a framework to collect data from digital libraries and websites of selected universities in Pakistan. We then identify researchers working in multiple research areas using clique percolation and present results of our analyses.
Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion, 2017
kuwait journal of science, 2016
Online bibliographic databases are providing significant resources to conduct analysis of academi... more Online bibliographic databases are providing significant resources to conduct analysis of academic social networks.We believe that work of an author is always influenced by work of his or her co-authors. In this study, we investigatethe impact of productivity and quality of work of an author’s co-authors on his or her ranking along with his owncontribution. We propose mutual influence (MI) based ranking method, which ranks authors based on (1) Publicationsof an author, along with impact of publications of his or her co-authors, (2) Normalized author position based Citationsweight, which is calculated from the citations received by an author with respect to position of his or her name in theco-authors list, (3) MINCC that combines the impact of both factors. A series of experiments has been conducted andresults show that proposed approach has capability to ranks authors in a significant way.
COVID-19 emerged in Wuhan and is later declared as a pandemic by World Health Organization. Diffe... more COVID-19 emerged in Wuhan and is later declared as a pandemic by World Health Organization. Different-aged people have varying gender-wise immunity control properties that necessitates understanding COVID-19 impact on age and gender which does not exist, currently. In this paper, COVID-19 surveillance variables are extensively studied along with hospitalization, tests-performed, and recovery data. Dataset is curated from three sources; however, age and gender data belong to Belgium, particularly. Visualizations, frequencies, Pearson’s and polyserial correlation, student’s t-test, and Cramer’s V are used for enhanced analysis. Results show higher mortality rate in males and need of more ventilators to combat severe symptoms.
kuwait journal of science, 2016
Machine learning and Statistical techniques are powerful analysis tools yet to be incorporated in... more Machine learning and Statistical techniques are powerful analysis tools yet to be incorporated in the new multidisciplinary field diversely termed as natural language processing (NLP) or computational linguistic. The linguistic knowledge may be ambiguous or contains ambiguity; therefore, various NLP tasks are carried out in order to resolve the ambiguity in speech and language processing.The current prevailing techniques for addressing various NLP tasks as a supervised learning are hidden Markov models (HMM), conditional random field (CRF), maximum entropy models (MaxEnt), support vector machines (SVM), Naive Bays, and deep learning (DL).The goal of this survey paper is to highlight ambiguity in speech and language processing, to provide brief overview of basic categories of linguistic knowledge, to discuss different existing machine learning models and their classification into different categories and finally to provide a comprehensive review of different state of the art machine ...
Library Hi Tech, 2021
Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scie... more Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scientific research. However, citation advantage varies from discipline to discipline, subject to subject and topic to topic. This study aims to compare the citation advantage of open access and toll access articles from four subfields of computer science. Design/methodology/approach This research studies the articles published by two prestigious publishers: Springer and Elsevier in the author-pays charges model from 2011 to 2015. For experimentation, four sub-domains of computer science are selected including (a) artificial intelligence, (b) human–computer interaction, (c) computer vision and graphics, and (d) software engineering. The open-access and toll-based citation advantage is studied and analyzed at the micro level within the computer science domain by performing independent sample t-tests. Findings The results of the study highlight that open access articles have a higher citation ...
Library Hi Tech, 2021
Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scie... more Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scientific research. However, citation advantage varies from discipline to discipline, subject to subject and topic to topic. This study aims to compare the citation advantage of open access and toll access articles from four subfields of computer science. Design/methodology/approach This research studies the articles published by two prestigious publishers: Springer and Elsevier in the author-pays charges model from 2011 to 2015. For experimentation, four sub-domains of computer science are selected including (a) artificial intelligence, (b) human–computer interaction, (c) computer vision and graphics, and (d) software engineering. The open-access and toll-based citation advantage is studied and analyzed at the micro level within the computer science domain by performing independent sample t-tests. Findings The results of the study highlight that open access articles have a higher citation ...
Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018
Players are ranked in various sports to show their importance over other players. Existing method... more Players are ranked in various sports to show their importance over other players. Existing methods only consider intra-type links (e.g., player to player and team to team), but ignore inter-type links (e.g., one type of player to another type of player, such as batsman to bowler and player to team) based on cognitive aspects. They also ignore the spatiality of the players. There is a strong relationship among players and their teams, which can be represented as a network consisting of multi-type interrelated objects. In this paper, we propose a players' ranking method, called Region-wise Players Link Fusion (RPLF) which is applied to the sport of cricket. RPLF considers players' region-wise intra-type and inter-type relation-based features to rank the players. Considering multi-type interrelated objects is based on the intuition that a batsman scoring high against top bowlers of a strong team or a bowler taking wickets against top batsmen of a strong team is considered as a good player. The experimental results show that RPLF provides promising insights of players' rankings. RLFP is a generic method and can be applied to different sports for ranking players.
COVID-19 has created anxiety not only in individuals but also in health organizations, and countr... more COVID-19 has created anxiety not only in individuals but also in health organizations, and countries worldwide. Not a single industry is left un-influenced and loss is being estimated in billions of dollars. The widespread of this pandemic disease has challenged researchers all over the world. Some of the researchers are working to invent its cure while, others are applying computing technologies to stop its spread, by analyzing and identifying patterns for prediction and forecasting. This is by no doubt the hottest area of research for the last 100 years. This survey has targeted the research published in computing sub-domains to combat the pandemic. The survey has clustered the scientific efforts into logical groups: surveillance, metrological effects, social media analytics, image processing and business and economy, analysis and modeling. It will serve as a leading source for the followings: researchers who want to identify what has been achieved in different computing sub-domai...
Entity resolution is a challenging and hot research area in the field of Information Systems sinc... more Entity resolution is a challenging and hot research area in the field of Information Systems since last decade. Author Name Disambiguation (AND) in Bibliographic Databases (BD) like DBLP , Citeseer , and Scopus is a specialized field of entity resolution. Given many citations of underlying authors, the AND task is to find which citations belong to the same author. In this survey, we start with three basic AND problems, followed by need for solution and challenges. A generic, five-step framework is provided for handling AND issues. These steps are; (1) Preparation of dataset (2) Selection of publication attributes (3) Selection of similarity metrics (4) Selection of models and (5) Clustering Performance evaluation. Categorization and elaboration of similarity metrics and methods are also provided. Finally, future directions and recommendations are given for this dynamic area of research.