Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765263
Shahla Nemati
Social networks’ comments are rich sources of information that may be fused with audio-visual contents to improve emotional video retrieval systems. The rationale behind this fusion is that different sources can complement each other since they have different natures, formats, and origins. Although emotional information expressed in users’ comments on the Web is in accordance with the emotional audio-visual content of videos, they are not synchronized. In order to address this problem, decision-level fusion is needed when such asynchronous modalities should be fused. In this article, a new decision-level fusion approach based on Ordered Weighted Averaging (OWA) operators is proposed. In this approach, emotion is first detected based on the audio, video, and users’ comments and then, individual decisions are fused using the OWA method. The proposed method is evaluated on the music videos of the standard DEAP data set. The results of comparing the proposed method with average, product, sum, and Dempster-Shafer fusion methods show that the proposed OWA-based method outperforms other methods in different fusion settings.
{"title":"OWA Operators for the Fusion of Social Networks’ Comments with Audio-Visual Content","authors":"Shahla Nemati","doi":"10.1109/ICWR.2019.8765263","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765263","url":null,"abstract":"Social networks’ comments are rich sources of information that may be fused with audio-visual contents to improve emotional video retrieval systems. The rationale behind this fusion is that different sources can complement each other since they have different natures, formats, and origins. Although emotional information expressed in users’ comments on the Web is in accordance with the emotional audio-visual content of videos, they are not synchronized. In order to address this problem, decision-level fusion is needed when such asynchronous modalities should be fused. In this article, a new decision-level fusion approach based on Ordered Weighted Averaging (OWA) operators is proposed. In this approach, emotion is first detected based on the audio, video, and users’ comments and then, individual decisions are fused using the OWA method. The proposed method is evaluated on the music videos of the standard DEAP data set. The results of comparing the proposed method with average, product, sum, and Dempster-Shafer fusion methods show that the proposed OWA-based method outperforms other methods in different fusion settings.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"409 1","pages":"90-95"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79837624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765252
Issa Annamoradnejad, J. Habibi
Twitter is among the most used microblogging and online social networking services. In Twitter, a name, phrase, or topic that is mentioned at a greater rate than others is called a "trending topic" or simply "trend". Twitter trends has shown their powerful ability in many public events, elections and market changes. Nevertheless, there has been very few works focusing on understanding the dynamics of these trending topics. In this article, we thoroughly examined the Twitter’s trending topics of 2018. To this end, we accessed Twitter’s trends API for the full year of 2018, and devised six criteria to evaluate our dataset. These six criteria are: lexical analysis, time to reach, trend reoccurrence, trending time, tweets count, and language analysis. In addition to providing general statistics and top trending topics regarding each criterion, we computed several distributions that explain this bulk of data.
{"title":"A Comprehensive Analysis of Twitter Trending Topics","authors":"Issa Annamoradnejad, J. Habibi","doi":"10.1109/ICWR.2019.8765252","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765252","url":null,"abstract":"Twitter is among the most used microblogging and online social networking services. In Twitter, a name, phrase, or topic that is mentioned at a greater rate than others is called a \"trending topic\" or simply \"trend\". Twitter trends has shown their powerful ability in many public events, elections and market changes. Nevertheless, there has been very few works focusing on understanding the dynamics of these trending topics. In this article, we thoroughly examined the Twitter’s trending topics of 2018. To this end, we accessed Twitter’s trends API for the full year of 2018, and devised six criteria to evaluate our dataset. These six criteria are: lexical analysis, time to reach, trend reoccurrence, trending time, tweets count, and language analysis. In addition to providing general statistics and top trending topics regarding each criterion, we computed several distributions that explain this bulk of data.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"86 1","pages":"22-27"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89131468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765289
Saeideh Fattahi, R. Yazdani, S. M. Vahidipour
Community structure detection in social networks has become a big challenge. Various methods in the literature have been presented to solve this challenge. Recently, several methods have also been proposed to solve this challenge based on a mapping-reduction model, in which data and algorithms are divided between different process nodes so that the complexity of time and memory of community detection in large social networks is reduced. In this paper, a mapping-reduction model is first proposed to detect the structure of communities. Then the proposed framework is rewritten according to a new mechanism called distributed cache memory; distributed cache memory can store different values associated with different keys and, if necessary, put them at different computational nodes. Finally, the proposed rewritten framework has been implemented using SPARK tools and its implementation results have been reported on several major social networks. The performed experiments show the effectiveness of the proposed framework by varying the values of various parameters.
{"title":"Discovery of Society Structure in A Social Network Using Distributed Cache Memory","authors":"Saeideh Fattahi, R. Yazdani, S. M. Vahidipour","doi":"10.1109/ICWR.2019.8765289","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765289","url":null,"abstract":"Community structure detection in social networks has become a big challenge. Various methods in the literature have been presented to solve this challenge. Recently, several methods have also been proposed to solve this challenge based on a mapping-reduction model, in which data and algorithms are divided between different process nodes so that the complexity of time and memory of community detection in large social networks is reduced. In this paper, a mapping-reduction model is first proposed to detect the structure of communities. Then the proposed framework is rewritten according to a new mechanism called distributed cache memory; distributed cache memory can store different values associated with different keys and, if necessary, put them at different computational nodes. Finally, the proposed rewritten framework has been implemented using SPARK tools and its implementation results have been reported on several major social networks. The performed experiments show the effectiveness of the proposed framework by varying the values of various parameters.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"20 1","pages":"264-269"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85914895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
the blockchain is an emerging technology with a core of a distributed ledger of connected blocks consisting of immutable transactions with decentralized management. The importance of blockchain technology and its impact in different domains highlights the need for understanding and evaluation of this technology. Understanding and evaluating technology from different aspects requires identifying the characteristics and specific criteria of that technology. In this regard, in this paper, after discussing the subject literature, the concept of the blockchain platform is described and a number of selected blockchain platforms are examined. Besides, the high-level benchmarking of the platform is evaluated from two aspects of the expected features of the platforms and their architectural components. Finally, due to the importance and significance of the criteria and their frequency, a set of effective criteria is chosen and accordingly, selected platforms of the blockchain are analyzed.
{"title":"Proposing a Framework for Evaluating the Blockchain Platform","authors":"Zahra Moezkarimi, Fatemeh Abdollahei, Abuzar Arabsorkhi","doi":"10.1109/ICWR.2019.8765280","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765280","url":null,"abstract":"the blockchain is an emerging technology with a core of a distributed ledger of connected blocks consisting of immutable transactions with decentralized management. The importance of blockchain technology and its impact in different domains highlights the need for understanding and evaluation of this technology. Understanding and evaluating technology from different aspects requires identifying the characteristics and specific criteria of that technology. In this regard, in this paper, after discussing the subject literature, the concept of the blockchain platform is described and a number of selected blockchain platforms are examined. Besides, the high-level benchmarking of the platform is evaluated from two aspects of the expected features of the platforms and their architectural components. Finally, due to the importance and significance of the criteria and their frequency, a set of effective criteria is chosen and accordingly, selected platforms of the blockchain are analyzed.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"16 1","pages":"152-160"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81668095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/icwr.2019.8765249
{"title":"ICWR 2019 Author Index","authors":"","doi":"10.1109/icwr.2019.8765249","DOIUrl":"https://doi.org/10.1109/icwr.2019.8765249","url":null,"abstract":"","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89702182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765281
Leila M. Amini, M. Keyvanpour
XML keyword search, due to its importance and applicability, is known as a well-attentioned topic in the context of XML (query) processing. Over the years, many different approaches have been proposed in order to perform the process in an effective way. The analysis of the literature in this field addresses the lack of benefiting users’ potential and capabilities to improve the process. However, there are some user-centric studies that incorporated users in the process in some way; to the best of the authors' knowledge, there is not any focused research work the respected literature that leverages human computation ability in this regard. On the other side, taking advantages of humans computing and processing abilities is currently known as a well-experienced strategy to solve computing problems in different contexts. Specifically, in the field of database and query processing there are several seminal works that leveraged users' participation in order to improve the process. Following such an idea, in this paper a crowdsourcing-based XML keyword searching approach is proposed. In addition to explaining the conceptual architecture and details of different parts of the proposed approach, the efficiency of the introduced approach is proved through conducting some experiments. The authors believe that the presented solution, as the first step, can provide a roadmap for the future works in the field.
{"title":"A Crowdsourcing-based Approach for Efficient XML Keyword Search","authors":"Leila M. Amini, M. Keyvanpour","doi":"10.1109/ICWR.2019.8765281","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765281","url":null,"abstract":"XML keyword search, due to its importance and applicability, is known as a well-attentioned topic in the context of XML (query) processing. Over the years, many different approaches have been proposed in order to perform the process in an effective way. The analysis of the literature in this field addresses the lack of benefiting users’ potential and capabilities to improve the process. However, there are some user-centric studies that incorporated users in the process in some way; to the best of the authors' knowledge, there is not any focused research work the respected literature that leverages human computation ability in this regard. On the other side, taking advantages of humans computing and processing abilities is currently known as a well-experienced strategy to solve computing problems in different contexts. Specifically, in the field of database and query processing there are several seminal works that leveraged users' participation in order to improve the process. Following such an idea, in this paper a crowdsourcing-based XML keyword searching approach is proposed. In addition to explaining the conceptual architecture and details of different parts of the proposed approach, the efficiency of the introduced approach is proved through conducting some experiments. The authors believe that the presented solution, as the first step, can provide a roadmap for the future works in the field.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"401 1","pages":"16-21"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79768541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765260
Shahin Ghadiri, S. Khorsandi
Data integration is a widely-used technique in wireless sensor networks. Security-aimed goals consisting of getting assurance about universality and correctness of data in data integration, while sensors are deployed in an enemy environment are truly vital. In this article, we have indicated that usage of the Bloom filters can satisfy our security goals. Furthermore, this technique, in comparison with existing methods, produces fewer overloads.
{"title":"Data Integration in Wireless Sensor Networks Using the Bloom Filters","authors":"Shahin Ghadiri, S. Khorsandi","doi":"10.1109/ICWR.2019.8765260","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765260","url":null,"abstract":"Data integration is a widely-used technique in wireless sensor networks. Security-aimed goals consisting of getting assurance about universality and correctness of data in data integration, while sensors are deployed in an enemy environment are truly vital. In this article, we have indicated that usage of the Bloom filters can satisfy our security goals. Furthermore, this technique, in comparison with existing methods, produces fewer overloads.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"14 1","pages":"74-78"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85830744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765257
H. Sadr, Mojdeh Nazari Soleimandarabi, M. Pedram, M. Teshnelab
Over the last decades, a multitude of semantic relatedness measures have been proposed. Despite an extensive amount of work dedicated to this area of research, the understanding of their foundation is still limited in real-world applications. In this paper, a unifying approach representing topic-based models is proposed and from which the state-of-the-art semantic relatedness measures are divided into two distinct types of topic-based and ontology-based models. Regardless of extensive researches in the field of ontology-based models, topic-based models have not been taken into account considerably. Consequently, the unified approach is able to highlight equivalences among these models and propose bridges between their theoretical bases. On the other hand, presenting a comprehensive unifying approach of topic-based models induces readers to have a common understanding of them despite the differences and complexities between their architecture and configuration details. In order to evaluate topic-based models in comparison to ontology-based models, comprehensive experiments in the application of semantic relatedness of geographic phrases have been applied. Empirical results have demonstrated that not only topic-based models in comparison to ontology-based models confront with fewer restrictions in the real world, but also their performance in computing semantic relatedness of geographic phrases is significantly superior to ontology-based models.
{"title":"Unified Topic-Based Semantic Models: A Study in Computing the Semantic Relatedness of Geographic Terms","authors":"H. Sadr, Mojdeh Nazari Soleimandarabi, M. Pedram, M. Teshnelab","doi":"10.1109/ICWR.2019.8765257","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765257","url":null,"abstract":"Over the last decades, a multitude of semantic relatedness measures have been proposed. Despite an extensive amount of work dedicated to this area of research, the understanding of their foundation is still limited in real-world applications. In this paper, a unifying approach representing topic-based models is proposed and from which the state-of-the-art semantic relatedness measures are divided into two distinct types of topic-based and ontology-based models. Regardless of extensive researches in the field of ontology-based models, topic-based models have not been taken into account considerably. Consequently, the unified approach is able to highlight equivalences among these models and propose bridges between their theoretical bases. On the other hand, presenting a comprehensive unifying approach of topic-based models induces readers to have a common understanding of them despite the differences and complexities between their architecture and configuration details. In order to evaluate topic-based models in comparison to ontology-based models, comprehensive experiments in the application of semantic relatedness of geographic phrases have been applied. Empirical results have demonstrated that not only topic-based models in comparison to ontology-based models confront with fewer restrictions in the real world, but also their performance in computing semantic relatedness of geographic phrases is significantly superior to ontology-based models.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"13 1","pages":"134-140"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89808862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765269
Razieh Adelkhah, M. Shamsfard, Niloofar Naderian
In this paper, we describe our proposed methodology for constructing an ontology of natural language processing (NLP). We use a semi-automatic method; a combination of rule-based and machine learning techniques; to construct and populate an ontology with bilingual (English-Persian) concept labels (lexicon) and evaluate it manually. This methodology results in a complete ontology in the natural language processing domain with 887 concepts, 88 relations, and 71 features. The built ontology is populated with near 36000 NLP related papers and 32000 authors, and about 201000 "is_Related_to", 83500 "is_Author_of", and 29000 "Presented_in" relations. The instantiation is done to enable applications find experts, publications and institutions related to various topics in NLP field.
{"title":"The Ontology of Natural Language Processing","authors":"Razieh Adelkhah, M. Shamsfard, Niloofar Naderian","doi":"10.1109/ICWR.2019.8765269","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765269","url":null,"abstract":"In this paper, we describe our proposed methodology for constructing an ontology of natural language processing (NLP). We use a semi-automatic method; a combination of rule-based and machine learning techniques; to construct and populate an ontology with bilingual (English-Persian) concept labels (lexicon) and evaluate it manually. This methodology results in a complete ontology in the natural language processing domain with 887 concepts, 88 relations, and 71 features. The built ontology is populated with near 36000 NLP related papers and 32000 authors, and about 201000 \"is_Related_to\", 83500 \"is_Author_of\", and 29000 \"Presented_in\" relations. The instantiation is done to enable applications find experts, publications and institutions related to various topics in NLP field.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"12 1","pages":"128-133"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90121630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-01DOI: 10.1109/ICWR.2019.8765293
Masoud Shayganmehr, G. Montazer
With the development of new technologies in the world, governments have tendency to make a communications with people and business with the help of such technologies. Electronic government (e-government) is defined as utilizing information technologies such as electronic networks, Internet and mobile phones by organizations and state institutions in order to making wide communication between citizens, business and different state institutions.Development of e-government starts with making website in order to share information with users and is considered as the main infrastructure for further development. Website assessment is considered as a way for improving service quality. Different international researches have introduced various indexes for website assessment, they only see some dimensions of website in their research. In this paper, the most important indexes for website quality assessment based on accurate review of previous studies are "Web design", "navigation", services", "maintenance and Support", "Citizens Participation", "Information Quality", "Privacy and Security", "Responsiveness", "Usability". Considering mentioned indexes in designing the website facilitates user interaction with the e-government websites.
{"title":"Identifying Indexes Affecting the Quality of E-Government Websites","authors":"Masoud Shayganmehr, G. Montazer","doi":"10.1109/ICWR.2019.8765293","DOIUrl":"https://doi.org/10.1109/ICWR.2019.8765293","url":null,"abstract":"With the development of new technologies in the world, governments have tendency to make a communications with people and business with the help of such technologies. Electronic government (e-government) is defined as utilizing information technologies such as electronic networks, Internet and mobile phones by organizations and state institutions in order to making wide communication between citizens, business and different state institutions.Development of e-government starts with making website in order to share information with users and is considered as the main infrastructure for further development. Website assessment is considered as a way for improving service quality. Different international researches have introduced various indexes for website assessment, they only see some dimensions of website in their research. In this paper, the most important indexes for website quality assessment based on accurate review of previous studies are \"Web design\", \"navigation\", services\", \"maintenance and Support\", \"Citizens Participation\", \"Information Quality\", \"Privacy and Security\", \"Responsiveness\", \"Usability\". Considering mentioned indexes in designing the website facilitates user interaction with the e-government websites.","PeriodicalId":6680,"journal":{"name":"2019 5th International Conference on Web Research (ICWR)","volume":"49 1","pages":"167-171"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79220377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：