Content-based social tagging recommendation, which considers the relationship between the tags and the descriptions contained in resources, is proposed to remedy the cold-start problem of collaborative filtering. There is such a common phenomenon that certain tag does not appear in the corresponding description, however, they do semantically relate with each other. State-of-the-art methods seldom consider this phenomenon and thus still need to be improved. In this paper, we propose a novel content-based social tag ranking scheme, aiming to recommend the semantic tags that the descriptions may not contain. The scheme firstly acquires the quantized semantic relationships between words with empirical methods, then constructs the weighted tag-digraph based on the descriptions and acquired quantized semantics, and finally performs a modified graph-based ranking algorithm to refine the score of each candidate tag for recommendation. Experimental results on both English and Chinese datasets show that the proposed scheme performs better than several state-of-the-art content-based methods.
{"title":"Content-Based Semantic Tag Ranking for Recommendation","authors":"M. Fan, Qiang Zhou, T. Zheng","doi":"10.1109/WI-IAT.2012.32","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.32","url":null,"abstract":"Content-based social tagging recommendation, which considers the relationship between the tags and the descriptions contained in resources, is proposed to remedy the cold-start problem of collaborative filtering. There is such a common phenomenon that certain tag does not appear in the corresponding description, however, they do semantically relate with each other. State-of-the-art methods seldom consider this phenomenon and thus still need to be improved. In this paper, we propose a novel content-based social tag ranking scheme, aiming to recommend the semantic tags that the descriptions may not contain. The scheme firstly acquires the quantized semantic relationships between words with empirical methods, then constructs the weighted tag-digraph based on the descriptions and acquired quantized semantics, and finally performs a modified graph-based ranking algorithm to refine the score of each candidate tag for recommendation. Experimental results on both English and Chinese datasets show that the proposed scheme performs better than several state-of-the-art content-based methods.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"333 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":"131474349","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 present a multi-agent cognitive architecture in which reactive and sequential processes can dynamically influence each other to insure that behaviour is responsive to current context (behavioural and situational) while sensitive to the longer term behavioural sequences needed to solve complex problems. We present the implementation of such a system using an agent based approach and illustrate its processing trough the simulation of two psychological tasks.
{"title":"A Multi Scale Cognitive Architecture to Account for the Adaptive and Reflective Nature of Behaviour","authors":"O. Larue, P. Poirier, R. Nkambou","doi":"10.1109/WI-IAT.2012.255","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.255","url":null,"abstract":"We present a multi-agent cognitive architecture in which reactive and sequential processes can dynamically influence each other to insure that behaviour is responsive to current context (behavioural and situational) while sensitive to the longer term behavioural sequences needed to solve complex problems. We present the implementation of such a system using an agent based approach and illustrate its processing trough the simulation of two psychological tasks.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"2 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":"130759098","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}
In recent years, social networking services have come into wide use to people. Especially, one of micro blog services, Twitter is a significant service. Twitter user gets information by following other users whose tweets match his interest. Retweet is one of Twitter functions which spreads tweets to other users. Using retweets, one can read tweets originated by users who are not followed by him. Our goal is to discover Twitter users who retweet many tweets which match the interest. We focus on the propagation of retweets and build a graph, the Overlap Graph, which contains users who share same retweets. Finally, we validate the users appearing in the graph by checking the frequency and the content of their retweets.
{"title":"Discovery of Interesting Users in Twitter by Overlapping Propagation Paths of Retweets","authors":"Yusuke Ota, Kazutaka Maruyama, M. Terada","doi":"10.1109/WI-IAT.2012.110","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.110","url":null,"abstract":"In recent years, social networking services have come into wide use to people. Especially, one of micro blog services, Twitter is a significant service. Twitter user gets information by following other users whose tweets match his interest. Retweet is one of Twitter functions which spreads tweets to other users. Using retweets, one can read tweets originated by users who are not followed by him. Our goal is to discover Twitter users who retweet many tweets which match the interest. We focus on the propagation of retweets and build a graph, the Overlap Graph, which contains users who share same retweets. Finally, we validate the users appearing in the graph by checking the frequency and the content of their retweets.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"13 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":"131438801","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}
Jian Chen, Guanliang Chen, H. Zhang, Jin Huang, Gansen Zhao
Social recommendation methods, often taking only one kind of relationship in social network into consideration, still faces the data sparsity and cold-start user problems. This paper presents a novel recommendation method based on multi-relational analysis: first, combine different relation networks by applying optimal linear regression analysis, and then, based on the optimal network combination, put forward a recommendation algorithm combined with multi-relational social network. The experimental results on Epinions dataset indicate that, compared with existing algorithms, can effectively alleviate data sparsity as well as cold-start issues, and achieve better performance.
{"title":"Social Recommendation Based on Multi-relational Analysis","authors":"Jian Chen, Guanliang Chen, H. Zhang, Jin Huang, Gansen Zhao","doi":"10.1109/WI-IAT.2012.222","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.222","url":null,"abstract":"Social recommendation methods, often taking only one kind of relationship in social network into consideration, still faces the data sparsity and cold-start user problems. This paper presents a novel recommendation method based on multi-relational analysis: first, combine different relation networks by applying optimal linear regression analysis, and then, based on the optimal network combination, put forward a recommendation algorithm combined with multi-relational social network. The experimental results on Epinions dataset indicate that, compared with existing algorithms, can effectively alleviate data sparsity as well as cold-start issues, and achieve better performance.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"130 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":"124251993","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}
In this paper we describe how culture and personality form important influences on the decision making processes of persons. When designing agents for serious games and simulations we need to take these aspects into consideration in order to create realistic behavior for the agents. We propose to model culture and personality as separate modules in the agent architecture in order to separate the domain dependent decision rules for action from the general sociological rules governing these aspects. We illustrate with an example how the architecture works.
{"title":"Close Encounters of the Agent Kind: Designing Agents for Effective Training","authors":"F. Dignum, Virginia Dignum, C. Jonker","doi":"10.1109/WI-IAT.2012.74","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.74","url":null,"abstract":"In this paper we describe how culture and personality form important influences on the decision making processes of persons. When designing agents for serious games and simulations we need to take these aspects into consideration in order to create realistic behavior for the agents. We propose to model culture and personality as separate modules in the agent architecture in order to separate the domain dependent decision rules for action from the general sociological rules governing these aspects. We illustrate with an example how the architecture works.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"14 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":"117056613","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}
In this paper we attempt to retrieve the items in the long-tail for top-N recommendation. That is, to recommend products that the end-user likes, but that are not generally popular, which has been getting more and more notice lately. By analysing the existing issue of current recommendation algorithms, a strategy is proposed that succeeds in maintaining recommendation accuracy while reducing the concentration of the recommendation on popular items in the system. Evaluating on the publicly available Movie lens and Yahoo! datasets, the results show the recommendation algorithm proposed in this work retrieves items in the users' relatively unpopular tastes without losing the performance in their popular tastes, which ultimately results in a better overall accuracy for the system.
{"title":"A Double-Ranking Strategy for Long-Tail Product Recommendation","authors":"Mi Zhang, N. Hurley, Wei Li, X. Xue","doi":"10.1109/WI-IAT.2012.20","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.20","url":null,"abstract":"In this paper we attempt to retrieve the items in the long-tail for top-N recommendation. That is, to recommend products that the end-user likes, but that are not generally popular, which has been getting more and more notice lately. By analysing the existing issue of current recommendation algorithms, a strategy is proposed that succeeds in maintaining recommendation accuracy while reducing the concentration of the recommendation on popular items in the system. Evaluating on the publicly available Movie lens and Yahoo! datasets, the results show the recommendation algorithm proposed in this work retrieves items in the users' relatively unpopular tastes without losing the performance in their popular tastes, which ultimately results in a better overall accuracy for the system.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"19 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":"122007251","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}
Online social network has become prevalent in our modern lifestyle by which one can easily connect and share information with anybody around the world. Facebook, Twitter, Flicker, Sina Weibo, are some exemplars nowadays. As the population of users in social networks grows, the concern of security in using such network escalates too. The social network is formed by people from all walks of life. Since there is little physical interaction available, it is difficult to verify whether social network users are trustworthy or not. In this paper, we propose a method that assists users to infer the degree of trustworthiness in social network. A quantitative indicator, which we call it Trust Index (TI) is assigned to each user, so one can have a ranked list of users, those with the greatest values of TI appear on top and vice versa. This serves as a reference for a user to decide how much s/he would want to trust them in social networks. TI is calculated based on the distance in terms of hop counts that measures how far apart between the user and s/he peer is. The distance is estimated by referring to relation as well as how acquainted the test user is with respect to some verified icons (public figures which have already been verified by the social network administrators) in social networks. Our TI algorithm also could enlist a group of people whose TIs fall below a given threshold, these are the users that need to be cautious about.
{"title":"Not Every Friend on a Social Network Can be Trusted: An Online Trust Indexing Algorithm","authors":"R. Tang, Luke Lu, Zhuang Yan, S. Fong","doi":"10.1109/WI-IAT.2012.84","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.84","url":null,"abstract":"Online social network has become prevalent in our modern lifestyle by which one can easily connect and share information with anybody around the world. Facebook, Twitter, Flicker, Sina Weibo, are some exemplars nowadays. As the population of users in social networks grows, the concern of security in using such network escalates too. The social network is formed by people from all walks of life. Since there is little physical interaction available, it is difficult to verify whether social network users are trustworthy or not. In this paper, we propose a method that assists users to infer the degree of trustworthiness in social network. A quantitative indicator, which we call it Trust Index (TI) is assigned to each user, so one can have a ranked list of users, those with the greatest values of TI appear on top and vice versa. This serves as a reference for a user to decide how much s/he would want to trust them in social networks. TI is calculated based on the distance in terms of hop counts that measures how far apart between the user and s/he peer is. The distance is estimated by referring to relation as well as how acquainted the test user is with respect to some verified icons (public figures which have already been verified by the social network administrators) in social networks. Our TI algorithm also could enlist a group of people whose TIs fall below a given threshold, these are the users that need to be cautious about.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"47 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":"128576388","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}
This paper considers the problem of self-interested agents engaged in costly exploration when individual findings benefit all agents. The purpose of the exploration is to reason about the nature and value of the different opportunities available to the agents whenever such information is a priori unknown. While the problem has been considered for the case where the goal is to maximize the overall expected benefit, the focus of this paper is on settings where the agents are self-interested, i.e, each agent's goal is to maximize its individual expected benefit. The paper presents an equilibrium analysis of the model, considering both mixed and pure equilibria. The analysis is used to demonstrate two somehow non-intuitive properties of the equilibrium cooperative exploration strategies used by the agents and their resulting expected payoffs: (a) when using mixed equilibrium strategies, the agents might lose due to having more potential opportunities available for them in their environment, and (b) if the agents can have additional agents join them in the exploration they might prefer the less competent ones to join the process.
{"title":"Join Me with the Weakest Partner, Please","authors":"Moshe Mash, Igor Rochlin, David Sarne","doi":"10.1109/WI-IAT.2012.155","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.155","url":null,"abstract":"This paper considers the problem of self-interested agents engaged in costly exploration when individual findings benefit all agents. The purpose of the exploration is to reason about the nature and value of the different opportunities available to the agents whenever such information is a priori unknown. While the problem has been considered for the case where the goal is to maximize the overall expected benefit, the focus of this paper is on settings where the agents are self-interested, i.e, each agent's goal is to maximize its individual expected benefit. The paper presents an equilibrium analysis of the model, considering both mixed and pure equilibria. The analysis is used to demonstrate two somehow non-intuitive properties of the equilibrium cooperative exploration strategies used by the agents and their resulting expected payoffs: (a) when using mixed equilibrium strategies, the agents might lose due to having more potential opportunities available for them in their environment, and (b) if the agents can have additional agents join them in the exploration they might prefer the less competent ones to join the process.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"35 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":"130125982","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}
In this paper, we observe that the user preference styles tend to change regularly following certain patterns. Therefore, we propose a Preference Pattern model to capture the user preference styles and their temporal dynamics, and apply this model to improve the accuracy of the Top-N recommendation. Precisely, a preference pattern is defined as a set of user preference styles sorted in a time order. The basic idea is to model user preference styles and their temporal dynamics by constructing a representative subspace with an Expectation-Maximization (EM)-like algorithm, which works in an iterative fashion by refining the global and the personal preference styles simultaneously. Then, the degree which the recommendations match the active user's preference styles, can be estimated by measuring its reconstruction error from its projection on the representative subspace. The experiment results indicate that the proposed model is robust to the data sparsity problem, and can significantly outperform the state-of-the-art algorithms on the Top-N recommendation in terms of accuracy.
{"title":"Learning User Preference Patterns for Top-N Recommendations","authors":"Yongli Ren, Gang Li, Wanlei Zhou","doi":"10.1109/WI-IAT.2012.102","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.102","url":null,"abstract":"In this paper, we observe that the user preference styles tend to change regularly following certain patterns. Therefore, we propose a Preference Pattern model to capture the user preference styles and their temporal dynamics, and apply this model to improve the accuracy of the Top-N recommendation. Precisely, a preference pattern is defined as a set of user preference styles sorted in a time order. The basic idea is to model user preference styles and their temporal dynamics by constructing a representative subspace with an Expectation-Maximization (EM)-like algorithm, which works in an iterative fashion by refining the global and the personal preference styles simultaneously. Then, the degree which the recommendations match the active user's preference styles, can be estimated by measuring its reconstruction error from its projection on the representative subspace. The experiment results indicate that the proposed model is robust to the data sparsity problem, and can significantly outperform the state-of-the-art algorithms on the Top-N recommendation in terms of accuracy.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"134 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":"131031571","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}
L. V. Moergestel, E. Puik, Daniël Telgen, J. Meyer
To meet the requirements of modern production, where short time to market, production driven by customer requirements and low cost small quantity production are important issues, we have been developing an agent-based software infrastructure for agile industrial production. This production is done on special devices called equip lets. A grid of these equip lets connected by a fast network is capable of producing a variety of different products in parallel. The multi-agent-based software infrastructure is responsible for the agile manufacturing. An important aspect of this software is the scheduling of the production. This paper describes a multi-agent-based solution for this problem. In our production system requests for products arrive at random times and every product must be completed before its deadline.
{"title":"Production Scheduling in an Agile Agent-Based Production Grid","authors":"L. V. Moergestel, E. Puik, Daniël Telgen, J. Meyer","doi":"10.1109/WI-IAT.2012.139","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.139","url":null,"abstract":"To meet the requirements of modern production, where short time to market, production driven by customer requirements and low cost small quantity production are important issues, we have been developing an agent-based software infrastructure for agile industrial production. This production is done on special devices called equip lets. A grid of these equip lets connected by a fast network is capable of producing a variety of different products in parallel. The multi-agent-based software infrastructure is responsible for the agile manufacturing. An important aspect of this software is the scheduling of the production. This paper describes a multi-agent-based solution for this problem. In our production system requests for products arrive at random times and every product must be completed before its deadline.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"21 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":"130622679","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：