Pub Date : 2009-12-18DOI: 10.1109/ICDIM.2009.5356782
A. Chua, C. S. Lee, D. Goh, R. Ang
Mobile media sharing has become an increasingly commonly activity. Using a dairy study, we investigated motivations behind mobile media sharing. Participants maintained a month-long diary, documenting their media sharing activities. Post-study interviews were also conducted to elicit additional information. Results suggest a range of motivational factors for media sharing behavior. These include personal and social influences. Participants were also more inclined to share photos than with any other media due to cost and transmission time considerations. Implications of our work are discussed.
{"title":"Motivations for media sharing among mobile phone users","authors":"A. Chua, C. S. Lee, D. Goh, R. Ang","doi":"10.1109/ICDIM.2009.5356782","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356782","url":null,"abstract":"Mobile media sharing has become an increasingly commonly activity. Using a dairy study, we investigated motivations behind mobile media sharing. Participants maintained a month-long diary, documenting their media sharing activities. Post-study interviews were also conducted to elicit additional information. Results suggest a range of motivational factors for media sharing behavior. These include personal and social influences. Participants were also more inclined to share photos than with any other media due to cost and transmission time considerations. Implications of our work are discussed.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121860654","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356795
Seyed Iman Mirrezaei, Javad Shahparian, M. Ghodsi
One of the challenges of P2P systems is to perform load balancing efficiently. A distributed hash table (DHT) abstraction, heterogeneous nodes, and non uniform distribution of objects cause load imbalance in structured P2P overlay networks. Several solutions are suggested to solve this problem but they have some restrictions. They assume the homogeneous capabilities of nodes, unawareness of the link latency during transferring load and imposing logical structures to collect and reassign load. This paper presents a distributed load balancing algorithm with topology awareness using the concept of virtual servers. In our proposed approach, each node collects neighborhood load information from physically close nodes and reassigns virtual servers to overlay nodes according to topology of underlying network. Consequently, it provides rapid convergence on load balance and reduces the load transfer cost. Moreover, our parametric algorithm increases the quality of load balancing among close nodes of overlay and also provides a new tradeoff between the quality of load balancing and load transfer cost among all overlay nodes. Our simulations show that our approach reduces the load transfer cost and saves a great network bandwidth.
{"title":"A topology-aware load balancing algorithm for P2P systems","authors":"Seyed Iman Mirrezaei, Javad Shahparian, M. Ghodsi","doi":"10.1109/ICDIM.2009.5356795","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356795","url":null,"abstract":"One of the challenges of P2P systems is to perform load balancing efficiently. A distributed hash table (DHT) abstraction, heterogeneous nodes, and non uniform distribution of objects cause load imbalance in structured P2P overlay networks. Several solutions are suggested to solve this problem but they have some restrictions. They assume the homogeneous capabilities of nodes, unawareness of the link latency during transferring load and imposing logical structures to collect and reassign load. This paper presents a distributed load balancing algorithm with topology awareness using the concept of virtual servers. In our proposed approach, each node collects neighborhood load information from physically close nodes and reassigns virtual servers to overlay nodes according to topology of underlying network. Consequently, it provides rapid convergence on load balance and reduces the load transfer cost. Moreover, our parametric algorithm increases the quality of load balancing among close nodes of overlay and also provides a new tradeoff between the quality of load balancing and load transfer cost among all overlay nodes. Our simulations show that our approach reduces the load transfer cost and saves a great network bandwidth.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"495 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132415629","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356784
Grant D. Fryia, Renata Wachowiak-Smolíkova, M. Wachowiak
As computer systems continue to improve, they also often become larger and more complicated. This may create barriers for individuals with cognitive and learning disabilities, who may find these systems more difficult to use. In this paper, an approach incorporating recent research into interface accessibility for assistive technology is taken to improve the usability of an e-Learning system. By developing a prototype without unnecessary complexities or distractions and by retaining and enhancing those features that are required, this type of e-Learning system can meet the needs of its intended users.
{"title":"Human-computer interface design in an e-Learning system for individuals with cognitive and learning disabilities","authors":"Grant D. Fryia, Renata Wachowiak-Smolíkova, M. Wachowiak","doi":"10.1109/ICDIM.2009.5356784","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356784","url":null,"abstract":"As computer systems continue to improve, they also often become larger and more complicated. This may create barriers for individuals with cognitive and learning disabilities, who may find these systems more difficult to use. In this paper, an approach incorporating recent research into interface accessibility for assistive technology is taken to improve the usability of an e-Learning system. By developing a prototype without unnecessary complexities or distractions and by retaining and enhancing those features that are required, this type of e-Learning system can meet the needs of its intended users.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128864698","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356778
S. Stamou, Paraskevi Tzekou, Nikos Zotos
A number of scientific publications discuss works that have been financially supported by agencies that invest in research. We refer to those publications as funded research works. In this paper, we try to capture the impact of funded research works, in order to assist funding agencies evaluate their efficacy in identifying the best research efforts. To accomplish our goal, we firstly need a method that automatically identifies publications that correspond to funded research. Our proposed method leverages NLP techniques in order to identify acknowledgments of financial support in the publications' content. Publications containing acknowledgments of financial support are deemed as funded works. Following the identification of funded research articles, we quantify their impact by considering the number of their citations, their freshness as well as the impact of their publication venue. The application of our method to a number of publications reveals that although funded research articles account to nearly 23% of the scientific publications, their average impact is increased compared to the average impact of non-funded publications. Our findings suggest that investments made on research deliver significant results and that funding agencies are effective in judging the potential impact of research efforts.
{"title":"Quantifying the impact of funded research works","authors":"S. Stamou, Paraskevi Tzekou, Nikos Zotos","doi":"10.1109/ICDIM.2009.5356778","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356778","url":null,"abstract":"A number of scientific publications discuss works that have been financially supported by agencies that invest in research. We refer to those publications as funded research works. In this paper, we try to capture the impact of funded research works, in order to assist funding agencies evaluate their efficacy in identifying the best research efforts. To accomplish our goal, we firstly need a method that automatically identifies publications that correspond to funded research. Our proposed method leverages NLP techniques in order to identify acknowledgments of financial support in the publications' content. Publications containing acknowledgments of financial support are deemed as funded works. Following the identification of funded research articles, we quantify their impact by considering the number of their citations, their freshness as well as the impact of their publication venue. The application of our method to a number of publications reveals that although funded research articles account to nearly 23% of the scientific publications, their average impact is increased compared to the average impact of non-funded publications. Our findings suggest that investments made on research deliver significant results and that funding agencies are effective in judging the potential impact of research efforts.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126523237","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356797
Asmidar Abu Bakar, Roslan Ismail, A. Ahmad, J. Manan, J. Jais
Mobile ad-hoc network is a network that can dynamically setup on the fly by mobile nodes. Due to its unique characteristics, it is becoming an attractive choice for commercial and also military application and among the used is to support information sharing among mobile nodes. However due to its borderless infrastructure, this network is highly susceptible to adversaries nodes, that illegally able to access information shared in the network. Hence to overcome this problem we proposed a Group Based Access Control scheme, a step by step process or protocol that able to make an access to share information in the network secure. We use emergency rescue mission scenario to illustrate the use of the scheme. The protocol created meets the security properties such as data confidentiality, integrity and also non-repudiation.
{"title":"Group based access control scheme (GBAC): Keeping information sharing secure in mobile Ad- hoc environment","authors":"Asmidar Abu Bakar, Roslan Ismail, A. Ahmad, J. Manan, J. Jais","doi":"10.1109/ICDIM.2009.5356797","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356797","url":null,"abstract":"Mobile ad-hoc network is a network that can dynamically setup on the fly by mobile nodes. Due to its unique characteristics, it is becoming an attractive choice for commercial and also military application and among the used is to support information sharing among mobile nodes. However due to its borderless infrastructure, this network is highly susceptible to adversaries nodes, that illegally able to access information shared in the network. Hence to overcome this problem we proposed a Group Based Access Control scheme, a step by step process or protocol that able to make an access to share information in the network secure. We use emergency rescue mission scenario to illustrate the use of the scheme. The protocol created meets the security properties such as data confidentiality, integrity and also non-repudiation.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128264831","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356799
Oliver Batz, Carsten Kleiner, Arne Koschel
Peer-to-Peer (P2P) networks promise to be a means for secure, reliable and effective data distribution. This paper describes the p2pcds project, which requires such features for a closed distributed advertising system. In this system large multimedia files are to be shared for simultaneous display on a large number of advertising screens. The project delivers a new and improved P2P based approach for a currently available client-server system. p2pcds utilizes P2P networks for a decentral network structure and includes peers for data distribution to get a fast and reliable system. It also establishes multipoint connections via IP-multicast to increase the data transfer rate. Other features include a public-key- infrastructure for secure decentral authentication and a kind of a two-phase commit for concurrent data transfers. Presented are p2pcds concepts and some details about its implementation with Java and JXTA.
{"title":"P2P applied in CMS for advertising","authors":"Oliver Batz, Carsten Kleiner, Arne Koschel","doi":"10.1109/ICDIM.2009.5356799","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356799","url":null,"abstract":"Peer-to-Peer (P2P) networks promise to be a means for secure, reliable and effective data distribution. This paper describes the p2pcds project, which requires such features for a closed distributed advertising system. In this system large multimedia files are to be shared for simultaneous display on a large number of advertising screens. The project delivers a new and improved P2P based approach for a currently available client-server system. p2pcds utilizes P2P networks for a decentral network structure and includes peers for data distribution to get a fast and reliable system. It also establishes multipoint connections via IP-multicast to increase the data transfer rate. Other features include a public-key- infrastructure for secure decentral authentication and a kind of a two-phase commit for concurrent data transfers. Presented are p2pcds concepts and some details about its implementation with Java and JXTA.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"33 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116727083","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356763
Byung-Won On, Ingyu Lee
When non-unique values are used as the identifier of entities, due to their homonym, confusion can occur. In particular, when part of “names” of entities are used as their identifiers, the problem is often referred to as a mixed entity resolution problem, where goal is to sort out the erroneous entities due to name homonyms (e.g., if only last name is used as an identifier, one cannot distinguish “Vannevar Bush” from “George Bush”). Especially, a mixed entity resolution problem is common on the Web data. For instance, to search for a product name (e.g., Oracle) in Google, there exist a mixture of web pages due to the name homonyms (e.g., Oracle Database, Oracle Audio, Oracle Academy, etc.). In this paper, we present a practical system for resolving such mixed entities on the Web. For development of such a system, we propose a web service based interface, an unsu-pervised clustering scheme, and cluster ranking algorithms. In particular, since the correct number of clusters is often unknown, we study a state-of-the-art unsupervised clustering solution based on propagation of pairwise similarities of entities. Our claim is empirically validated via experimentation, showing that our approach outperforms main competing solution.
{"title":"Google based name search: Resolving mixed entities on the web","authors":"Byung-Won On, Ingyu Lee","doi":"10.1109/ICDIM.2009.5356763","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356763","url":null,"abstract":"When non-unique values are used as the identifier of entities, due to their homonym, confusion can occur. In particular, when part of “names” of entities are used as their identifiers, the problem is often referred to as a mixed entity resolution problem, where goal is to sort out the erroneous entities due to name homonyms (e.g., if only last name is used as an identifier, one cannot distinguish “Vannevar Bush” from “George Bush”). Especially, a mixed entity resolution problem is common on the Web data. For instance, to search for a product name (e.g., Oracle) in Google, there exist a mixture of web pages due to the name homonyms (e.g., Oracle Database, Oracle Audio, Oracle Academy, etc.). In this paper, we present a practical system for resolving such mixed entities on the Web. For development of such a system, we propose a web service based interface, an unsu-pervised clustering scheme, and cluster ranking algorithms. In particular, since the correct number of clusters is often unknown, we study a state-of-the-art unsupervised clustering solution based on propagation of pairwise similarities of entities. Our claim is empirically validated via experimentation, showing that our approach outperforms main competing solution.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132512508","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356796
Hasan Al-Hamadi, Maytham Safar, Dariush Ebrahimi
A wireless sensor network (WSN) is a form of network that consists of randomly distributed devices/nodes in a known space. In this kind of environment there are two major concerns that governs the efficiency, availability and functionality of the network, namely power consumption and fault tolerance. This paper introduces a new algorithm that is Power Efficient Cluster Algorithm (PECA). The main focus of the proposed algorithm is to reduce the power consumption required to setup the network since it is the stage where power is used the most. This is achieved by reducing the total number of radio transmission required for the network setup. As a fault tolerance approach the algorithm stores some information about each node for easier recovery of the network should any node fails in the network. The proposed algorithm is compared with Self Organizing Sensor (SOS) algorithm; the result shows that PECA consume significantly less power than SOS.
{"title":"Power efficient clustering algorithm","authors":"Hasan Al-Hamadi, Maytham Safar, Dariush Ebrahimi","doi":"10.1109/ICDIM.2009.5356796","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356796","url":null,"abstract":"A wireless sensor network (WSN) is a form of network that consists of randomly distributed devices/nodes in a known space. In this kind of environment there are two major concerns that governs the efficiency, availability and functionality of the network, namely power consumption and fault tolerance. This paper introduces a new algorithm that is Power Efficient Cluster Algorithm (PECA). The main focus of the proposed algorithm is to reduce the power consumption required to setup the network since it is the stage where power is used the most. This is achieved by reducing the total number of radio transmission required for the network setup. As a fault tolerance approach the algorithm stores some information about each node for easier recovery of the network should any node fails in the network. The proposed algorithm is compared with Self Organizing Sensor (SOS) algorithm; the result shows that PECA consume significantly less power than SOS.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131916487","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356786
Yaling Liu, A. Agah
This paper introduces a non-traditional Web search problem, referred to as “process-based search”, and focuses on the query analysis and formulation of this type of search. Traditional information retrieval models were created based on the assumption that one query can be answered by one document. A query needs to properly specify the topic being requested. Recently published work, referred to as subtopic retrieval or aspect retrieval, has relaxed this assumption that a query may contain multiple subtopics and it can be answered by a set of documents, each of which covers one or multiple subtopics. However, the original query was still assumed to explicitly specify the subtopics. Process-based search further relaxes the assumption to facilitate complex Web searches. The subtopics of the query do not have to be explicitly specified, because the user may not be able to do so in the initial search due to the lack of knowledge for the topic. A database of processes is used to discover the subtopics implied by the query. Thus, this type of search is called process-based search. This paper focuses on the algorithms for formulating sub-queries for the process-based search. Experiments on real data sets showed that the needs of process-based searching exist in the real world and the proposed concepts and approaches effectively solve this problem.
{"title":"Query operations of process-based searches","authors":"Yaling Liu, A. Agah","doi":"10.1109/ICDIM.2009.5356786","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356786","url":null,"abstract":"This paper introduces a non-traditional Web search problem, referred to as “process-based search”, and focuses on the query analysis and formulation of this type of search. Traditional information retrieval models were created based on the assumption that one query can be answered by one document. A query needs to properly specify the topic being requested. Recently published work, referred to as subtopic retrieval or aspect retrieval, has relaxed this assumption that a query may contain multiple subtopics and it can be answered by a set of documents, each of which covers one or multiple subtopics. However, the original query was still assumed to explicitly specify the subtopics. Process-based search further relaxes the assumption to facilitate complex Web searches. The subtopics of the query do not have to be explicitly specified, because the user may not be able to do so in the initial search due to the lack of knowledge for the topic. A database of processes is used to discover the subtopics implied by the query. Thus, this type of search is called process-based search. This paper focuses on the algorithms for formulating sub-queries for the process-based search. Experiments on real data sets showed that the needs of process-based searching exist in the real world and the proposed concepts and approaches effectively solve this problem.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131336024","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 : 2009-12-18DOI: 10.1109/ICDIM.2009.5356764
K. Denecke
Motivated by the numerous applications of analysing opinions in multi-domain scenarios, this paper studies the potential of a still rarely considered approach to the problem of multi-domain sentiment analysis based on Senti-WordNet as lexical resource. SentiWordNet scores are exploited together with additional features to assign a polarity to a text using machine learning. On the other hand, a rule-based approach is studied based on sentiment scores. The introduced methods are tested on single domains of a real-world data set consisting of documents in six different domains, but also in cross-domain settings. The results show that for cross-domain sentiment analysis rule-based approaches with fix opinion lexica are unsuited. For machine-learning based sentiment classification a mixture of documents of different domains achieves good results.
{"title":"Are SentiWordNet scores suited for multi-domain sentiment classification?","authors":"K. Denecke","doi":"10.1109/ICDIM.2009.5356764","DOIUrl":"https://doi.org/10.1109/ICDIM.2009.5356764","url":null,"abstract":"Motivated by the numerous applications of analysing opinions in multi-domain scenarios, this paper studies the potential of a still rarely considered approach to the problem of multi-domain sentiment analysis based on Senti-WordNet as lexical resource. SentiWordNet scores are exploited together with additional features to assign a polarity to a text using machine learning. On the other hand, a rule-based approach is studied based on sentiment scores. The introduced methods are tested on single domains of a real-world data set consisting of documents in six different domains, but also in cross-domain settings. The results show that for cross-domain sentiment analysis rule-based approaches with fix opinion lexica are unsuited. For machine-learning based sentiment classification a mixture of documents of different domains achieves good results.","PeriodicalId":300287,"journal":{"name":"2009 Fourth International Conference on Digital Information Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129991264","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：