For sentiment classification, there exist a heterogeneous mass of resources such as semantic dictionaries, unlabeled corpora, and heuristic rules. In this paper, based on a graph-based semi-supervised algorithm, we focus on exploiting multiple resources to construct similarity matrices which are fused by simple but effective schemes. We reported encouraging results of the experiments in sentiment classification, which indicate that the adopted algorithm can utilize multiple resources to improve performance.
{"title":"Using Multiple Resources in Graph-Based Semi-supervised Sentiment Classification","authors":"Ge Xu, Houfeng Wang","doi":"10.1109/WI-IAT.2012.18","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.18","url":null,"abstract":"For sentiment classification, there exist a heterogeneous mass of resources such as semantic dictionaries, unlabeled corpora, and heuristic rules. In this paper, based on a graph-based semi-supervised algorithm, we focus on exploiting multiple resources to construct similarity matrices which are fused by simple but effective schemes. We reported encouraging results of the experiments in sentiment classification, which indicate that the adopted algorithm can utilize multiple resources to improve performance.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121252405","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}
We consider a problem of automated object description and clustering. Because traditional image-processing-based object recognition algorithms can only cluster objects in image-base, we propose a method to describe an object in human language and group similar objects together in text-processing way. This paper describes a system that recognizes objects with text labels printed on the surface of objects themselves or their packing cases. By analyzing them, objects could be described in English words, and then be clustered into corresponding groups.
{"title":"Semantic-Feature-Based Object Recognition by Using Internet Data Mining","authors":"Jing Xu, S. Okada, K. Nitta","doi":"10.1109/WI-IAT.2012.145","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.145","url":null,"abstract":"We consider a problem of automated object description and clustering. Because traditional image-processing-based object recognition algorithms can only cluster objects in image-base, we propose a method to describe an object in human language and group similar objects together in text-processing way. This paper describes a system that recognizes objects with text labels printed on the surface of objects themselves or their packing cases. By analyzing them, objects could be described in English words, and then be clustered into corresponding groups.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125251112","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}
J. Domenech, B. D. L. Ossa, A. Pont, J. A. Gil, Milagros Martinez, A. Rubio
The prompt availability of up-to-date economic indicators is crucial to monitor the economy and to steer the design of policies for promoting business innovation and raising firm competitiveness. Economic indicators usually suffer important lags since they are commonly obtained from official databases or from interviews to a sample of agents, thus limiting the representative ness and usefulness of the information. In a context in which the presence of companies in the World Wide Web is almost an obligation to succeed, corporate websites are connected, in some way, to the firm economic activity. On the basis of this relation, this paper proposes an intelligent system that analyzes corporate websites to produce web indicators related to the economic activity of the firms. This system has been successfully implemented and applied to infer company size characteristics from data gathered from corporate websites. Our results show that relatively large companies provide web content in a foreign language and use proprietary web servers.
{"title":"An Intelligent System for Retrieving Economic Information from Corporate Websites","authors":"J. Domenech, B. D. L. Ossa, A. Pont, J. A. Gil, Milagros Martinez, A. Rubio","doi":"10.1109/WI-IAT.2012.92","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.92","url":null,"abstract":"The prompt availability of up-to-date economic indicators is crucial to monitor the economy and to steer the design of policies for promoting business innovation and raising firm competitiveness. Economic indicators usually suffer important lags since they are commonly obtained from official databases or from interviews to a sample of agents, thus limiting the representative ness and usefulness of the information. In a context in which the presence of companies in the World Wide Web is almost an obligation to succeed, corporate websites are connected, in some way, to the firm economic activity. On the basis of this relation, this paper proposes an intelligent system that analyzes corporate websites to produce web indicators related to the economic activity of the firms. This system has been successfully implemented and applied to infer company size characteristics from data gathered from corporate websites. Our results show that relatively large companies provide web content in a foreign language and use proprietary web servers.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"43 s6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120839458","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 occurrence of major emergencies would have a certain impact on the production of related enterprises, industry outlook, even on national macroeconomic situation. The impact is presented as price fluctuation of event-related enterprises' stock. Fortunately, the web search data reflects the trends of investors' behavior and contains hundreds of millions of searchers' concerns and interests on the emergencies and the demand for stocks trading. Therefore, we propose the idea of applying web search data to study the fluctuation of stock market caused by major emergencies. Firstly, a systematic theoretical framework has been built to reveal the correlation between web search and major emergency. Secondly, at the theoretical framework basis, this paper analyzes the impact strength and impact period on stock market brought by major emergency through using web search data. Furthermore, we take 723 Yong Wen EMU (Electric Multiple Units) Accident as a typical research object to verify the relationship. The results show that goodness of fit reaches 0.888 by adding the web search index variable into the model, and confirm that web search data would accurately and timely characterize the impact of the EMU accident on the stock market fluctuation. Finally, based on GARCH model, we study the impact period of EMU accident on the stock market, which is about two months.
{"title":"An Impact Analysis of Emergency Event on Stock Market Based on Web Search Data: A Case from 723 Yongwen Railway Accident","authors":"Y. Xin, Benfu Lv, S. Yi, Geng Peng","doi":"10.1109/WI-IAT.2012.76","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.76","url":null,"abstract":"The occurrence of major emergencies would have a certain impact on the production of related enterprises, industry outlook, even on national macroeconomic situation. The impact is presented as price fluctuation of event-related enterprises' stock. Fortunately, the web search data reflects the trends of investors' behavior and contains hundreds of millions of searchers' concerns and interests on the emergencies and the demand for stocks trading. Therefore, we propose the idea of applying web search data to study the fluctuation of stock market caused by major emergencies. Firstly, a systematic theoretical framework has been built to reveal the correlation between web search and major emergency. Secondly, at the theoretical framework basis, this paper analyzes the impact strength and impact period on stock market brought by major emergency through using web search data. Furthermore, we take 723 Yong Wen EMU (Electric Multiple Units) Accident as a typical research object to verify the relationship. The results show that goodness of fit reaches 0.888 by adding the web search index variable into the model, and confirm that web search data would accurately and timely characterize the impact of the EMU accident on the stock market fluctuation. Finally, based on GARCH model, we study the impact period of EMU accident on the stock market, which is about two months.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122320716","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 evolution of the Web has allowed the generation of several platforms for collaborative work. One of the main contributors to these advances is the Open Source initiative, in which projects are boosted to a new level of interaction and cooperation that improves their software quality and reliability. In order to understand how the group of contributors interacts with the software under development, we propose a novel methodology that adapts Lotka-Volterra-based biological models used for host-parasite interaction. In that sense, we used the concept mutualism from social parasites. Preliminary results based on experiments on the Github collaborative platform showed that Open Source phenomena can be modeled as a mutualistic system, in terms of the evolution of the population of developers and repositories.
{"title":"Biological Mutualistic Models Applied to Study Open Source Software Development","authors":"Pablo Loyola, In-Young Ko","doi":"10.1109/WI-IAT.2012.228","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.228","url":null,"abstract":"The evolution of the Web has allowed the generation of several platforms for collaborative work. One of the main contributors to these advances is the Open Source initiative, in which projects are boosted to a new level of interaction and cooperation that improves their software quality and reliability. In order to understand how the group of contributors interacts with the software under development, we propose a novel methodology that adapts Lotka-Volterra-based biological models used for host-parasite interaction. In that sense, we used the concept mutualism from social parasites. Preliminary results based on experiments on the Github collaborative platform showed that Open Source phenomena can be modeled as a mutualistic system, in terms of the evolution of the population of developers and repositories.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122416945","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}
S. Hashimoto, Ryo Kanamori, Takayuki Ito, S. Chakraborty
Some auction systems are applied to the parking reservation system which would exert an important role in the next generation traffic systems. As an introduction evaluation of the auction systems for the parking reservation, we compare the results in case of a simultaneous auction and sequential one, and examine the influences of the strategy. Although the limited numerical experiment under the assumption that the number of parking space is only three, time zone is three, and also the total number of bidders are 25, the following results are obtained, 1) electricity trading makes a profit to both the parking manager and users 2) the average of the parking revenues would be the highest when the reservation price is a little higher than the expect bidding price.
{"title":"Evaluation of Parking Reservation System with Auction Including Electricity Trading","authors":"S. Hashimoto, Ryo Kanamori, Takayuki Ito, S. Chakraborty","doi":"10.1109/WI-IAT.2012.200","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.200","url":null,"abstract":"Some auction systems are applied to the parking reservation system which would exert an important role in the next generation traffic systems. As an introduction evaluation of the auction systems for the parking reservation, we compare the results in case of a simultaneous auction and sequential one, and examine the influences of the strategy. Although the limited numerical experiment under the assumption that the number of parking space is only three, time zone is three, and also the total number of bidders are 25, the following results are obtained, 1) electricity trading makes a profit to both the parking manager and users 2) the average of the parking revenues would be the highest when the reservation price is a little higher than the expect bidding price.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127774414","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}
Text analytics on consumer-generated content has gained significant momentum over last few years. A wide-range of text mining techniques has been proposed which can provide interesting insights about the text content. But, the challenge still exists in consuming the extracted information in form of actionable intelligence. Identifying actionable intelligence is difficult due to differences in consumer and business languages. Since feedbacks rarely talks of a single problem, determining the problems is also challenging. We propose a framework to address some of these challenges. Organizational websites or standard domain-ontologies are rich repositories of domain knowledge. The proposed method utilizes this knowledge to learn a discriminative classifier model for a domain using Fisher's discriminant metric. The consumer feedbacks are classified to different business categories using the learnt model. The output is further fed into a fuzzy reasoning unit where every feedback is assigned confidence values for each category. Initial experiments show that the proposed framework is capable of handling text feedbacks containing customer complaints in various domains.
{"title":"An Ontology-Based Mining of Consumer Feedbacks Using Fuzzy Reasoning","authors":"Lipika Dey, Sameera Bharadwaja H., Shefali Bhat","doi":"10.1109/WI-IAT.2012.193","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.193","url":null,"abstract":"Text analytics on consumer-generated content has gained significant momentum over last few years. A wide-range of text mining techniques has been proposed which can provide interesting insights about the text content. But, the challenge still exists in consuming the extracted information in form of actionable intelligence. Identifying actionable intelligence is difficult due to differences in consumer and business languages. Since feedbacks rarely talks of a single problem, determining the problems is also challenging. We propose a framework to address some of these challenges. Organizational websites or standard domain-ontologies are rich repositories of domain knowledge. The proposed method utilizes this knowledge to learn a discriminative classifier model for a domain using Fisher's discriminant metric. The consumer feedbacks are classified to different business categories using the learnt model. The output is further fed into a fuzzy reasoning unit where every feedback is assigned confidence values for each category. Initial experiments show that the proposed framework is capable of handling text feedbacks containing customer complaints in various domains.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128997475","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}
Location information is becoming prevalent in today's online social networks (OSNs), which raises special privacy concerns with regard to both location sharing and its applications. Even when no explicit location is disclosed by a user, it is possible to geolocate the user through his/her social context, e.g., status updates and social relationships in OSNs. To demonstrate this, we propose GeoFind, which accurately identifies users' geographic regions through effective fusion (re-ranking) of (1) text-based ranking using geo-sensitive textual features and (2) structure-based ranking using maximum likelihood estimation (MLE) of geotagged friends. Evaluation results using 0.8 million geotagged Twitter users over a 3-month period demonstrate that GeoFind outperforms state-of-the-art techniques, with significant reduction of estimation error (25% of average error, 66% of median error). The potential of improving location accuracy through the fusion of multiple data types calls for a re-examination of existing privacy protection policies and mechanisms.
{"title":"Fusing Text and Frienships for Location Inference in Online Social Networks","authors":"Hansu Gu, Haojie Hang, Q. Lv, D. Grunwald","doi":"10.1109/WI-IAT.2012.243","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.243","url":null,"abstract":"Location information is becoming prevalent in today's online social networks (OSNs), which raises special privacy concerns with regard to both location sharing and its applications. Even when no explicit location is disclosed by a user, it is possible to geolocate the user through his/her social context, e.g., status updates and social relationships in OSNs. To demonstrate this, we propose GeoFind, which accurately identifies users' geographic regions through effective fusion (re-ranking) of (1) text-based ranking using geo-sensitive textual features and (2) structure-based ranking using maximum likelihood estimation (MLE) of geotagged friends. Evaluation results using 0.8 million geotagged Twitter users over a 3-month period demonstrate that GeoFind outperforms state-of-the-art techniques, with significant reduction of estimation error (25% of average error, 66% of median error). The potential of improving location accuracy through the fusion of multiple data types calls for a re-examination of existing privacy protection policies and mechanisms.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125143470","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}
Group behaviors of organisms can be described as the response to personally and socially acquired information. Many previous works, for example traditional social force model and alignment rule, concern the influence of neighbors' behaviors, but overlook the individual direct response to the information of environment. Here, we propose a novel friction based social force model and focus on the individual initiative, which is a direct response to environmental stimuli. By employing multi-agent methods, our model simulates a grazing case: a group of sheep graze in a meadow. We demonstrate that, guided by friction force (namely the individual initiative of unwilling to move), initiatives of individual and partners have variable influences on the benefit and motion of individuals in group behaviors. Furthermore, simulation results are consistent with two recent biological observations, that cannot be mimicked by traditional social force model and alignment rule.
{"title":"A Friction Based Social Force Model for Group Behaviors","authors":"Zhaofeng Li, Yichuan Jiang","doi":"10.1109/WI-IAT.2012.112","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.112","url":null,"abstract":"Group behaviors of organisms can be described as the response to personally and socially acquired information. Many previous works, for example traditional social force model and alignment rule, concern the influence of neighbors' behaviors, but overlook the individual direct response to the information of environment. Here, we propose a novel friction based social force model and focus on the individual initiative, which is a direct response to environmental stimuli. By employing multi-agent methods, our model simulates a grazing case: a group of sheep graze in a meadow. We demonstrate that, guided by friction force (namely the individual initiative of unwilling to move), initiatives of individual and partners have variable influences on the benefit and motion of individuals in group behaviors. Furthermore, simulation results are consistent with two recent biological observations, that cannot be mimicked by traditional social force model and alignment rule.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128085838","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}
As an effective technique for dimensionality reduction, feature selection has a broad application in different research areas. In this paper, we present a feature selection method based on a novel feature clustering procedure, which aims at partitioning the features into different clusters such that the features in the same cluster contain similar structural information of the given instances. Subsequently, since the obtained feature subset consists of features from variant clusters, the similarity between selected features will be low. This allows us to reserve the most data structural information with the minimum number of features. Experimental results on different benchmark data sets demonstrate the superiority of the proposed method.
{"title":"Unsupervised Feature Selection with Feature Clustering","authors":"Yiu-ming Cheung, Hong Jia","doi":"10.1109/WI-IAT.2012.259","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.259","url":null,"abstract":"As an effective technique for dimensionality reduction, feature selection has a broad application in different research areas. In this paper, we present a feature selection method based on a novel feature clustering procedure, which aims at partitioning the features into different clusters such that the features in the same cluster contain similar structural information of the given instances. Subsequently, since the obtained feature subset consists of features from variant clusters, the similarity between selected features will be low. This allows us to reserve the most data structural information with the minimum number of features. Experimental results on different benchmark data sets demonstrate the superiority of the proposed method.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126394803","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：