检索结果-内蒙古大学图书馆

34th Information Systems Education Conference, ISECON 2018

作者： Sharif, Nauman Afzal, Muhammad Tanvir Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Capital University of Science and Technology Islamabad Pakistan

Social media has been already extensively used in e-learning context. Users produce a vast amount of learning resources on the web using technologies such as tweets, blogs and wikis. It is a daunting task for learners to select the appropriate resources according to their learning styles." One core area in Technology enhanced Learning deals with this information overload. Learning resources metadata features such as Title, Author, Category and keyword are used in literature to provide recommendation. However these metadata features have not been exploited for twitter based recommender systems. A comprehensive evaluations and experimentations are conducted to determine the effectiveness of resource metadata for twitter based e-learning recommendation. The detailed evaluation reveals the effectiveness of the resource metadata for twitter based e-learning recommendation. © 2018 34th Information Systems Education Conference. All Rights Reserved

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Twitter recommendation: Unary metadata features evaluation with TF/IDF using n-grams 34

Twitter recommendation: Unary metadata features evaluation w...

引用

34th Information Systems Education Conference, ISECON 2018

作者： Sharif, Nauman Afzal, Muhammad Tanvir Ahmed, Usman Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Capital University of Science and Technology Islamabad Pakistan Capital University of Science and Technology Islamabad Pakistan

Twitter has been identified by many researchers as a useful tool to assist e-Learners. However, contemporary e-learning systems have not fully utilized the strength of twitter to recommend learning resources. In literature metadata of learning resources such as title, author, category and keyword are used to provide recommendation. The aim of this paper is to evaluate the effectiveness of resource metadata for twitter based recommendation. A comprehensive evaluations and experimentations are carried out to validate the effectiveness of resource metadata for twitter based recommendation. A gold standard was formed with 220 research papers and 2957 related tweets collected from domain experts. © 2018 34th Information Systems Education Conference. All Rights Reserved

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Can Twitter be useful for e-learning recommendation? 33

Can Twitter be useful for e-learning recommendation?

引用

33rd Information Systems Education Conference, ISECON 2016

Twitter provides an opportunity to share various learning material along with short and precise text. Micro-blogging community is ever expanding. Discovery of the most relevant learning material becomes essential to solve the information overload problem. There is a potential need to provide twitter based learning recommendation for the learner without directly inferring the tool. E-learning recommender systems have been successfully supporting the individual leaning process. However there is a gap between the e-learning recommender system and twitter based recommendation such that no existing e-learning recommender systems are utilizing the twitter. This paper presents the work-in-progress with the aim to develop recommender system. Personalize learning activities and related tasks can be recommended to the learner according to the individual need of learner and as a result overall learning experience can be enhanced. In literature personalized recommender systems employs the characteristics of items, profiles of users and history of users and items interaction in order to recommend the related items. In this paper we shall investigate if the twitter can be useful for e-learning recommendation and what are the parameters that should be consider when recommending e-learning resources. © 2016 33rd Information Systems Education Conference. All Rights Reserved

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Recommendation approaches for E-learners - A survey 15

Recommendation approaches for E-learners - A survey

引用

7th ACM International Conference on Management of Computational and Collective IntElligence in Digital EcoSystems, MEDES 2015

作者： Sharif, Nauman Afzal, Muhammad Tanvir Institute for Knowledge Management Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9781450334808

Recommending relevant content to the learner is a challenging task for any e-Learning management system. This paper has critically reviewed the literature and identified the strategies being used to recommend relevant content to learners. This paper highlights the strength and limitations of prominent approaches and has presented challenging tasks which will be useful for the e-Learning research community to focus for the future research. © 2015 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

The web is big business

引用

Journal of computing and Information Technology 2015年第1期23卷 19-27页

作者： Mehmood, Rizwan Korica-Pehserl, Petra Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan Department of Computer Engineering University of Belgrade Serbia

As has been explained in the paper "A Survey of Communications and Collaborative Web Technologies" in this special issue the web started as a more or less one-way information system, allowing engineers at CERN to share new results in physics world-wide easily. As it developed, it becamemore and more a two-way (or more precisely a multi-way) communication tool, allowing to collaboratively work in many ways. This has, as it has been described in the aforementioned paper, not just changed how information is created and provided easy ways of communication, but has also allowed the growth of social networks as first tools to tie together the power of brains, changing how we work, think, do research, form new circles of people we are interested in. This on its own would have been a major change in how society works, yet it turned out soon that the technologies available would allow to set up completely new business models, and threaten some existing ones. Among the hundreds of million applications found on the web today, many set up to make money, or at least pay for themselves by providing excellent ways of advertisements. There is no person who could know all the applications available on the web, and there is no way to even list a tiny percentage of them. However, what we are trying in this paper is to classify applications and discuss their commercial or societal impact.

关键词： High energy physics

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on Emerging Technologies, ICET

作者： Qamar Mahmood Muhammad Abdul Qadir Muhammad Tanvir Afzal Center for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

Document similarity identification is one of the most significant problems of knowledge discovery and information retrieval. One way to perform these similarity measures is to analyze a citation graph of research papers. If we have document citation information in the form of RDF graph, how we may identify the document similarity measures by using social network analysis techniques? We have answered this question by applying semantic social network analysis techniques on RDF citation graphs of research papers to identify the pair wise similarity between these papers. For performing social network analysis we have used classes of centrality degree and closeness centrality from SemSNA ontology. Concept of minimum cut/maximum flow from graph theory is used for quantification of similarity measure. In our experiment we have used Citeseer data set; it is found that our results are promising as compared to manual similarity measures by human for a subset of this data set. Our results are also encouragingly comparable to other citation link analysis techniques as well as content based similarity measures; this is the reason that we have focused on RDF citation based similarity measure. In future we are looking forward to use some citation ontology (such as CITO) to improve RDF graph construction for our proposed similarity measure technique.

关键词： Social network services Resource description framework semantics Ontologies Algorithm design and analysis Fluid flow measurement Manuals

来源：评论

学校读者我要写书评

暂无评论

Knowledge discovery in hashtags#

Knowledge discovery in hashtags#

引用

International Conference on Emerging Technologies, ICET

作者： Rizwan Mehmood Hermann Maurer Muhammad Tanveer Afzal Institute for Information Systems and Computer Media Graz University of Technology Graz Austria Center for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

Twitter is a breed of social networks that are playing a buoyant role in today's world communication. This paper is an attempt to apply knowledge discovery process on Twitter dataset comprising hashtags along with the visual analytic techniques whose purpose is to provide information to the people in such a way so that they understand concealed knowledge in the data effortlessly and meritoriously. We further analyze tweet text and metadata associated with each tweet for identification of useful patterns like "who talks to whom" and "how much". Our research reveals the impact of visualization and hierarchical clustering technique in analyzing similar groups of users. Further we investigate different social network measures that unveil the influence of users in the particular hashtags.

关键词： Twitter Data visualization Knowledge discovery Data mining Libraries Communities

来源：评论

学校读者我要写书评

暂无评论

Exploiting Title-Keywords Relation to Develop Concept Classifier for Scientific Community

引用

4th International Conference on Networked Digital Technologies, NDT 2012

作者： Khan, Sher Afgun Afzal, Muhammad Tanvir Qadir, Muhammad Abdul Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Pakistan

ISBN: (纸本)9783642305665

The exponential growth of scientific resources on the web has raised scalability issues like quick retrieval of relevant resource. The major obstacle is attributed to unstructured nature of information. It is estimated that the scientific knowledge is doubling in every five years. This information is being indexed by search engines, citation indexes, and digital libraries etc. Most of the time, the indexed information is unstructured or semi-structured. Therefore, the users are unable to find the relevant research papers. Users are given thousands and sometimes millions of irrelevant hits. This is mainly due to the unstructured nature of information being stored. For a query, the information retrieval may be restricted to the relevant resources if the resources are structured in a classification. Some classifications are being used in different domains such as in computer science, the ACM classification scheme is being used to structure the research papers. However, the ACM classification was majorly updated in 1998 and does not include evolving concepts and domains since then. Furthermore, only ACM papers are classified using ACM classification scheme while other publishers normally do not use this classification. Therefore, the automatic classification becomes a major challenge for scientific community. Several approaches are being used for creating automatic classification on the basis of co-occurrence analysis, keywords analysis, and using domain models, etc. However, the current approaches have their limitations. In this paper, we proposed and implemented a new approach of finding the evolving classification, termed as concept classifier for the scientific community by aggregating the correlation between title terms and keywords of the paper. Initially the experiment has been conducted over the dataset of journal i.e. Journal of Universal Computer Science (***). The resultant taxonomy has been verified and compared with the Growbag dataset (DBLP dataset of co

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

semantic Aware Implication and Satisfiability for Conjunctive Queries in semantic Caching

Semantic Aware Implication and Satisfiability for Conjunctiv...

引用

4th International Conference on Networked Digital Technologies, NDT 2012

作者： Abbas, Muhammad Azeem Qadir, Muhammad Abdul Ahmad, Munir Ali, Tariq Center for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9783642305061

Finding satisfiability and implication results among queries is fundamental to several problems in databases especially in distributed databases. The known complexity of finding satisfiability of term S is O({pipe}S{pipe}3). Similarly complexity of finding "Is S implies T (S→T)" is O(S3+K) Where {pipe}S{pipe} is the number of distinct predicate attributes in S, and K is the number of predicate terms in T (S and T are conjunctive select-project-join(PSJ) queries). We show that with the induction of Cross Attribute Knowledge (CRA) the above complexity is reduced to O({pipe}S - CRA{pipe}3) and O({pipe}S - CRA{pipe}3+K) for satisfiability and implication respectively. © Springer-Verlag Berlin Heidelberg 2012.

关键词： Formal logic

来源：评论

学校读者我要写书评

暂无评论

ERRAGMap: Visualization tool

ERRAGMap: Visualization tool

引用

8th International Conference on Information Science and Digital Content Technology, ICIDT 2012

作者： Gillani, Saira Naz, Sheneela Naeem, Muhammad Afzal, Muhammad Tanvir Qayyum, Amir M. A. Jinnah University Islamabad Pakistan Center of Excellence in Data Mining M. A. Jinnah University Islamabad Pakistan Distributed and Semantic Computing M. A. Jinnah University Islamabad Pakistan

ISBN: (纸本)9788988678695

Earthquakes are considered one of the major disastrous situations for any nation. The horrible earthquake may claim hundreds of lives, thousands of injuries and demolishing thousands of houses. When an earthquake hits a nation then number of management bodies (such as: government organizations, non-government organizations (NGOs)) are actively involved in reinstating the damages. Generally, these organizations deal with stats of build and still-to-be build infrastructure (roads, buildings, and houses etc). Currently, this information is presented to the organizations as a raw text in huge amount. Therefore, it becomes difficult to highlight key areas where an immediate start of rehabilitation process is inevitable. In the past, some systems have been developed to present such information in structured form by using some visualization techniques. However, these tools are inadequate because of the following reasons: 1) Most of these tools are about geotechnical conditions of effected area and can provide help to describe seismic hazards 2) Some systems show trends of earthquakes in specific region. 3). None of the systems describe the rehabilitation process in an easily conceivable way. Therefore, this becomes an interesting and challenging research problem to build such a system that can overcome the above mentioned limitations of current techniques and systems. In this research, we present such a system called ERRAGMAP. This geo spatial tool discovers and presents deep insight into the data related to rehabilitation of the destroyed houses in the earthquake affected areas. Our contributions in this research are as follows: 1) critical analysis of existing tools of visualization for earthquake rehabilitation systems 2) propose and develop a framework for converting raw data into actionable knowledge, 3) propose, develop and evaluate an innovative visualization technique. © 2012 AICIT.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：