Pub Date : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814702
T. Ramya, S. Malathi, G. R. Pratheeksha, Visvam Devadoss Ambeth Kumar
Security as a condition is the degree of resistance to, or protection from harm. Securing gadgets in a way that is simple for the user to deploy yet, stringent enough to deny any malware intrusions onto the protected circle is investigated to find a balance between the extremes. Basically, the dominant approach on current control access is via password or PIN, but its flaw is being clearly documented. An application (to be incorporated in a mobile phone) that allows the user's gadget to be used as a Biometric Capture device in addition to serve as a Biometric Signature acquisition device for processing a multi-level authentication procedure to allow access to any specific Web Service of exclusive confidentiality is proposed. To evaluate the lucidness of the proposed procedure, a specific set of domain specifications to work on are chosen and the accuracy of the Biometric face Recognition carried out is evaluated along with the compatibility of the Application developed with different sample inputs. The results obtained are exemplary compared to the existing other devices to suit a larger section of the society through the Internet for improving the security.
{"title":"Personalized authentication procedure for restricted web service access in mobile phones","authors":"T. Ramya, S. Malathi, G. R. Pratheeksha, Visvam Devadoss Ambeth Kumar","doi":"10.1109/ICADIWT.2014.6814702","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814702","url":null,"abstract":"Security as a condition is the degree of resistance to, or protection from harm. Securing gadgets in a way that is simple for the user to deploy yet, stringent enough to deny any malware intrusions onto the protected circle is investigated to find a balance between the extremes. Basically, the dominant approach on current control access is via password or PIN, but its flaw is being clearly documented. An application (to be incorporated in a mobile phone) that allows the user's gadget to be used as a Biometric Capture device in addition to serve as a Biometric Signature acquisition device for processing a multi-level authentication procedure to allow access to any specific Web Service of exclusive confidentiality is proposed. To evaluate the lucidness of the proposed procedure, a specific set of domain specifications to work on are chosen and the accuracy of the Biometric face Recognition carried out is evaluated along with the compatibility of the Application developed with different sample inputs. The results obtained are exemplary compared to the existing other devices to suit a larger section of the society through the Internet for improving the security.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124543801","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814691
Prema Nedungadi, Haripriya Harikumar, M. Ramesh
The high computational complexity of text classification is a significant problem with the growing surge in text data. An effective but computationally expensive classification is the k-nearest-neighbor (kNN) algorithm. Principal Component Analysis (PCA) has commonly been used as a preprocessing phase to reduce the dimensionality followed by kNN. However, though the dimensionality is reduced, the algorithm requires all the vectors in the projected space to perform the kNN. We propose a new hybrid algorithm that uses PCA & kNN but performs kNN with a small set of neighbors instead of the complete data vectors in the projected space, thus reducing the computational complexity. An added advantage in our method is that we are able to get effective classification using a relatively smaller number of principal components. New text for classification is projected into the lower dimensional space and kNN is performed only with the neighbors in each axis based on the principal that vectors that are closer in the original space are closer in the projected space and also along the projected components. Our findings with the standard benchmark dataset Reuters show that the proposed model significantly outperforms kNN and the standard PCA-kNN hybrid algorithms while maintaining similar classification accuracy.
{"title":"A high performance hybrid algorithm for text classification","authors":"Prema Nedungadi, Haripriya Harikumar, M. Ramesh","doi":"10.1109/ICADIWT.2014.6814691","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814691","url":null,"abstract":"The high computational complexity of text classification is a significant problem with the growing surge in text data. An effective but computationally expensive classification is the k-nearest-neighbor (kNN) algorithm. Principal Component Analysis (PCA) has commonly been used as a preprocessing phase to reduce the dimensionality followed by kNN. However, though the dimensionality is reduced, the algorithm requires all the vectors in the projected space to perform the kNN. We propose a new hybrid algorithm that uses PCA & kNN but performs kNN with a small set of neighbors instead of the complete data vectors in the projected space, thus reducing the computational complexity. An added advantage in our method is that we are able to get effective classification using a relatively smaller number of principal components. New text for classification is projected into the lower dimensional space and kNN is performed only with the neighbors in each axis based on the principal that vectors that are closer in the original space are closer in the projected space and also along the projected components. Our findings with the standard benchmark dataset Reuters show that the proposed model significantly outperforms kNN and the standard PCA-kNN hybrid algorithms while maintaining similar classification accuracy.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133027699","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814677
A. Saju, I. Mary, A. Vasuki, P. S. Lakshmi
This paper proposes a novel content based image retrieval system incorporating the relevance feedback technique. In order to improve the retrieval accuracy of content based image retrieval systems, research focus has been shifted in reducing the semantic gap between visual features and the human semantics. The five major techniques available to narrow down the semantic gap are: (a) Object ontology (b) machine learning (c) relevance feedback (d) semantic template (e) web image retrieval. This paper focuses on the relevance feedback technique by which semantic gap can be reduced in order to improve the retrieval efficiency of the system. The major challenges facing the existing relevance feedback technique is the number of iterations and the execution time. The proposed algorithm provides a better solution to overcome both these challenges. The efficiency of the system can be calculated based on precision and recall.
{"title":"Reduction of semantic gap using relevance feedback technique in image retrieval system","authors":"A. Saju, I. Mary, A. Vasuki, P. S. Lakshmi","doi":"10.1109/ICADIWT.2014.6814677","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814677","url":null,"abstract":"This paper proposes a novel content based image retrieval system incorporating the relevance feedback technique. In order to improve the retrieval accuracy of content based image retrieval systems, research focus has been shifted in reducing the semantic gap between visual features and the human semantics. The five major techniques available to narrow down the semantic gap are: (a) Object ontology (b) machine learning (c) relevance feedback (d) semantic template (e) web image retrieval. This paper focuses on the relevance feedback technique by which semantic gap can be reduced in order to improve the retrieval efficiency of the system. The major challenges facing the existing relevance feedback technique is the number of iterations and the execution time. The proposed algorithm provides a better solution to overcome both these challenges. The efficiency of the system can be calculated based on precision and recall.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"55 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116385013","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814680
A. Ramesh, K. Srinivasa, N. Pramod
We introduce a graph and an intersection based technique which uses statistical and semantic analysis for computing relative importance of textual units in large data sets in order to summarize text. Current implementations consider only the mathematical/statistical approach to summarize text. (like frequency, TFIDF, etc.) But there are many cases where two completely different textual units might be semantically related. We hope to overcome this problem by exploiting the resources of WordNet and by the use of semantic graphs which represents the semantic dissimilarity between any pair of sentences. Ranking is usually performed on statistical information. The algorithm constructs semantic graphs using implicit links which are based on the semantic relatedness between text nodes and consequently ranks nodes using a ranking algorithm.
{"title":"SentenceRank — A graph based approach to summarize text","authors":"A. Ramesh, K. Srinivasa, N. Pramod","doi":"10.1109/ICADIWT.2014.6814680","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814680","url":null,"abstract":"We introduce a graph and an intersection based technique which uses statistical and semantic analysis for computing relative importance of textual units in large data sets in order to summarize text. Current implementations consider only the mathematical/statistical approach to summarize text. (like frequency, TFIDF, etc.) But there are many cases where two completely different textual units might be semantically related. We hope to overcome this problem by exploiting the resources of WordNet and by the use of semantic graphs which represents the semantic dissimilarity between any pair of sentences. Ranking is usually performed on statistical information. The algorithm constructs semantic graphs using implicit links which are based on the semantic relatedness between text nodes and consequently ranks nodes using a ranking algorithm.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116429858","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814663
V. U. Panchami, N. Radhika
Patient length of stay is the most commonly employed outcome measure for hospital resource consumption and to monitor the performance of the hospital. Predicting the patient's length of stay in a hospital is an important aspect for effective planning at various levels. It helps in efficient utilization of resources and facilities. So, there exist a strong demand to make accurate and robust models to predict length of stay. This paper analyzes various methods for length of stay prediction, its advantages and disadvantages and proposes a novel approach for predicting whether the length of stay of the patient is greater than one week. The approach uses DBSCAN clustering to create the training set for classification. The prediction models are compared using accuracy, precision and recall and found that using DBSCAN as a precursor to classification gives better results.
{"title":"A novel approach for predicting the length of hospital stay with DBSCAN and supervised classification algorithms","authors":"V. U. Panchami, N. Radhika","doi":"10.1109/ICADIWT.2014.6814663","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814663","url":null,"abstract":"Patient length of stay is the most commonly employed outcome measure for hospital resource consumption and to monitor the performance of the hospital. Predicting the patient's length of stay in a hospital is an important aspect for effective planning at various levels. It helps in efficient utilization of resources and facilities. So, there exist a strong demand to make accurate and robust models to predict length of stay. This paper analyzes various methods for length of stay prediction, its advantages and disadvantages and proposes a novel approach for predicting whether the length of stay of the patient is greater than one week. The approach uses DBSCAN clustering to create the training set for classification. The prediction models are compared using accuracy, precision and recall and found that using DBSCAN as a precursor to classification gives better results.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115668965","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814685
K. Nimmy, M. Sethumadhavan
Proper authentication is an essential technology for cloud-computing environments in which connections to external environments are common and risks are high. Here, a new scheme is proposed for mutual authentication where the user and cloud server can authenticate one another. The protocol is designed in such a way that it uses steganography as an additional encryption scheme. The scheme achieves authentication using secret sharing. Secret sharing allows a part of the secret to be kept in both sides which when combined becomes the complete secret. The secret contains information about both parties involved. Further, out of band authentication has been used which provides additional security. The proposed protocol provides mutual authentication and session key establishment between the users and the cloud server. Also, the users have been given the flexibility to change the password. Furthermore, strong security features makes the protocol well suited for the cloud environment.
{"title":"Novel mutual authentication protocol for cloud computing using secret sharing and steganography","authors":"K. Nimmy, M. Sethumadhavan","doi":"10.1109/ICADIWT.2014.6814685","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814685","url":null,"abstract":"Proper authentication is an essential technology for cloud-computing environments in which connections to external environments are common and risks are high. Here, a new scheme is proposed for mutual authentication where the user and cloud server can authenticate one another. The protocol is designed in such a way that it uses steganography as an additional encryption scheme. The scheme achieves authentication using secret sharing. Secret sharing allows a part of the secret to be kept in both sides which when combined becomes the complete secret. The secret contains information about both parties involved. Further, out of band authentication has been used which provides additional security. The proposed protocol provides mutual authentication and session key establishment between the users and the cloud server. Also, the users have been given the flexibility to change the password. Furthermore, strong security features makes the protocol well suited for the cloud environment.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126775904","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 business continuity is essential for any enterprise application where remote replication enables customers to store the data on a Logical Disk (LDisk) at the local site and replicate the same at remote locations. In case of a disaster at local site, the replicated LDisk (remote copy) at remote site is marked as primary copy and the remote copy is made available without any downtime. The replication to destination is configured either in sync-mode or async-mode. In case of async-mode, the host IOs are first processed by the source array at the local site. A snapshot of the LDisk is triggered periodically and the new snapshot is replicated to the destination array at remote site. In this configuration, one particular node of source array becomes loaded with ongoing host IOs, snapshot, and replication activities. In the scale-out model, a storage array consists of multiple nodes and hence, the replication tasks and responsibilities can be distributed to a different node. We propose a cloning mechanism called DeltaClone, which replicates the incremental changes of LDisk across nodes. The ownership of a LDisk and its DeltaClone are assigned to two different nodes which are called as master node and slave node respectively. When the periodic request is triggered to synchronize the LDisk data with its remote copy, the current DeltaClone is frozen and it is then merged with remote copy. Hence, the replication tasks are carried out at slave node without affecting the performance of the master node and the ongoing host IOs. The slave node is re-elected periodically to ensure the dynamic load-balancing across the nodes. Our distributed design improves the overall storage performance and the simulation results showed that the proposed method outperforms the traditional methods.
{"title":"A distributed system design for next generation storage and remote replication","authors":"Dhanaraj Maruthachalam, Taranisen Mohanta, Amulya Ratna Swain, Hemendra Kumar Sethi","doi":"10.1109/ICADIWT.2014.6814686","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814686","url":null,"abstract":"The business continuity is essential for any enterprise application where remote replication enables customers to store the data on a Logical Disk (LDisk) at the local site and replicate the same at remote locations. In case of a disaster at local site, the replicated LDisk (remote copy) at remote site is marked as primary copy and the remote copy is made available without any downtime. The replication to destination is configured either in sync-mode or async-mode. In case of async-mode, the host IOs are first processed by the source array at the local site. A snapshot of the LDisk is triggered periodically and the new snapshot is replicated to the destination array at remote site. In this configuration, one particular node of source array becomes loaded with ongoing host IOs, snapshot, and replication activities. In the scale-out model, a storage array consists of multiple nodes and hence, the replication tasks and responsibilities can be distributed to a different node. We propose a cloning mechanism called DeltaClone, which replicates the incremental changes of LDisk across nodes. The ownership of a LDisk and its DeltaClone are assigned to two different nodes which are called as master node and slave node respectively. When the periodic request is triggered to synchronize the LDisk data with its remote copy, the current DeltaClone is frozen and it is then merged with remote copy. Hence, the replication tasks are carried out at slave node without affecting the performance of the master node and the ongoing host IOs. The slave node is re-elected periodically to ensure the dynamic load-balancing across the nodes. Our distributed design improves the overall storage performance and the simulation results showed that the proposed method outperforms the traditional methods.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"438 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132863237","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814683
Jolanta Mizera-Pietraszko
As opposed to query reformulation oriented towards changes made by a user to specify the information need more precisely, a post-search query modeling is a technique of exploiting syntax variation of gradually extended query which depending on some other factors like e.g. the resource, database or the key word alignment, facilitates the searching process. The study into modeling query submitted to some search engines that utilize different translation semantic paradigms is motivated by a real-world's challenges to retrieve heterogeneous textual documents from the web. For a couple of language pairs, we develop a user-centered framework for imposing the Hidden Web traffic optimization. In literature Hidden Web is the World Wide Web facet usually missed by standard information systems. Our data set contains variety of query types submitted to translingual systems that perform a number of syntax-driven indexing being evaluated by constructing a precision trend function, the one that intensifies the relevance set of the system responses from a perspective of dramatic reduction of those outside the user's interest.
{"title":"Post-search query modeling in federated web scenario","authors":"Jolanta Mizera-Pietraszko","doi":"10.1109/ICADIWT.2014.6814683","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814683","url":null,"abstract":"As opposed to query reformulation oriented towards changes made by a user to specify the information need more precisely, a post-search query modeling is a technique of exploiting syntax variation of gradually extended query which depending on some other factors like e.g. the resource, database or the key word alignment, facilitates the searching process. The study into modeling query submitted to some search engines that utilize different translation semantic paradigms is motivated by a real-world's challenges to retrieve heterogeneous textual documents from the web. For a couple of language pairs, we develop a user-centered framework for imposing the Hidden Web traffic optimization. In literature Hidden Web is the World Wide Web facet usually missed by standard information systems. Our data set contains variety of query types submitted to translingual systems that perform a number of syntax-driven indexing being evaluated by constructing a precision trend function, the one that intensifies the relevance set of the system responses from a perspective of dramatic reduction of those outside the user's interest.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126512606","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814700
A. K. Mandal, A. Sarkar
Conceptualization of different aspects of cloud applications and formal representations of interactions among the different components of SaaS are most crucial issues towards the design of an effective cloud architectural framework. In this paper a graph-based specification called Cloud Service Architecture Graph (CSAG) has been proposed to model such interactions among various components of Software as a Service (SaaS). CSAG is capable of addressing several important aspects like extendibility, composability, analyzability etc. for SaaS based applications over cloud environment. Moreover, several properties of CSAG shows that the proposed approach is effective towards the design of a SaaS based applications. The proposed CSAG has been illustrated using the case study of Electronic Health Record (EHR) system over cloud environment.
{"title":"Formal representation of service interactions for SaaS based applications","authors":"A. K. Mandal, A. Sarkar","doi":"10.1109/ICADIWT.2014.6814700","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814700","url":null,"abstract":"Conceptualization of different aspects of cloud applications and formal representations of interactions among the different components of SaaS are most crucial issues towards the design of an effective cloud architectural framework. In this paper a graph-based specification called Cloud Service Architecture Graph (CSAG) has been proposed to model such interactions among various components of Software as a Service (SaaS). CSAG is capable of addressing several important aspects like extendibility, composability, analyzability etc. for SaaS based applications over cloud environment. Moreover, several properties of CSAG shows that the proposed approach is effective towards the design of a SaaS based applications. The proposed CSAG has been illustrated using the case study of Electronic Health Record (EHR) system over cloud environment.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115564410","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 : 2014-05-15DOI: 10.1109/ICADIWT.2014.6814688
S. Fong, S. Deb, Io-Weng Chan, P. Vijayakumar
It has become a prevalent lifestyle nowadays that netizens voice their opinions on social networks (Web 2.0), for matters of all sizes, and on a regular basis. The opinions which initially should be intended for their groups of friends propagate to all public users. This pond of opinions in the forms of forum posts, messages written on micro-blogs, Twitter and Facebook, are largely contributed by communities of online users (or sometimes bloggers). The messages though might seem to be trivial when each of them is viewed singularly, the converged sum of them serves as a potentially useful source of information to be analysed. A government of a city, for instance, may be interested to know the response of the citizens after a new policy is announced, from their voices collected from the Internet. However, such online messages are unstructured in nature, their contexts vary greatly, and that poses a tremendous difficulty in correctly interpreting them. In this paper we propose an innovative analytical model that evaluates such messages by representing them in different moods. The model comprises of several data analytics such as cultural moods analyzer implemented by neural networks, text mining and hierarchical visualization that reflects public moods over a large population of Internet comments.
{"title":"An event driven neural network system for evaluating public moods from online users' comments","authors":"S. Fong, S. Deb, Io-Weng Chan, P. Vijayakumar","doi":"10.1109/ICADIWT.2014.6814688","DOIUrl":"https://doi.org/10.1109/ICADIWT.2014.6814688","url":null,"abstract":"It has become a prevalent lifestyle nowadays that netizens voice their opinions on social networks (Web 2.0), for matters of all sizes, and on a regular basis. The opinions which initially should be intended for their groups of friends propagate to all public users. This pond of opinions in the forms of forum posts, messages written on micro-blogs, Twitter and Facebook, are largely contributed by communities of online users (or sometimes bloggers). The messages though might seem to be trivial when each of them is viewed singularly, the converged sum of them serves as a potentially useful source of information to be analysed. A government of a city, for instance, may be interested to know the response of the citizens after a new policy is announced, from their voices collected from the Internet. However, such online messages are unstructured in nature, their contexts vary greatly, and that poses a tremendous difficulty in correctly interpreting them. In this paper we propose an innovative analytical model that evaluates such messages by representing them in different moods. The model comprises of several data analytics such as cultural moods analyzer implemented by neural networks, text mining and hierarchical visualization that reflects public moods over a large population of Internet comments.","PeriodicalId":339627,"journal":{"name":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123973446","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：