Sentiment analysis refers to a broad range of fields of natural language processing, computational linguistics and text mining. Sentiment classification of reviews and comments has emerged as the most useful application in the area of sentiment analysis. Although sentiment classification generally is carried out at the document level, accurate results require analysis at the sentence level. Bag of words and feature based sentiment are the most popular approaches used by researchers to deal with sentiment classification of opinions about products such as movies, electronics, cars etc. Until recently most classification techniques have considered adjectives, adverbs and nouns as features. This paper proposes a new approach based on verb as an important opinion term particularly in social domains. We extract opinion structures which consider verb as the core element. Sentiment orientation is recognized from sentiments inside of opinion structures and their association with the social issue. Experimental results show that considering verbs improves the performance of sentiment classification.
{"title":"Verb Oriented Sentiment Classification","authors":"Mostafa Karamibekr, A. Ghorbani","doi":"10.1109/WI-IAT.2012.122","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.122","url":null,"abstract":"Sentiment analysis refers to a broad range of fields of natural language processing, computational linguistics and text mining. Sentiment classification of reviews and comments has emerged as the most useful application in the area of sentiment analysis. Although sentiment classification generally is carried out at the document level, accurate results require analysis at the sentence level. Bag of words and feature based sentiment are the most popular approaches used by researchers to deal with sentiment classification of opinions about products such as movies, electronics, cars etc. Until recently most classification techniques have considered adjectives, adverbs and nouns as features. This paper proposes a new approach based on verb as an important opinion term particularly in social domains. We extract opinion structures which consider verb as the core element. Sentiment orientation is recognized from sentiments inside of opinion structures and their association with the social issue. Experimental results show that considering verbs improves the performance of sentiment classification.","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":"133476982","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}
Mobile technologies may play a pivotal role in language learning in situations where multilingualism may be a key factor in personal and societal development. We review some Mobile Assisted Language Learning (MALL) studies and show that when such technologies take into account cognitive constraints and rely on a coherent pedagogy model they foster the learning process and allow to frame it in the socio-cultural environment of the learner.
{"title":"Cognitive-Educational Constraints for Socially-Relevant MALL Technologies","authors":"Tania Cerni, R. Job","doi":"10.1109/WI-IAT.2012.117","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.117","url":null,"abstract":"Mobile technologies may play a pivotal role in language learning in situations where multilingualism may be a key factor in personal and societal development. We review some Mobile Assisted Language Learning (MALL) studies and show that when such technologies take into account cognitive constraints and rely on a coherent pedagogy model they foster the learning process and allow to frame it in the socio-cultural environment of the learner.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"422 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113998454","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}
With his work on formal languages of recursion, Yiannis Moschovakis initiated development of a new approach to the mathematical notion of algorithm, beginning with work on the mathematics of algorithms in 1994. One of the most exciting potentials of the approach is for applications to computational semantics of artificial and natural languages. In particular, the typed version of theory of a cyclic recursion and its language reveal crucial properties of semantic concepts such as meaning and synonymy, from computational perspective. This paper is a brief introduction to Moschovakis' Type Theory of A cyclic Recursion and its system of reduction rules from the perspective of its applications to semantics of a class of modifiers. The formal language of a cyclic recursion and its theory have potentials for applications to algorithmic semantics of natural and artificial languages. The paper demonstrates the potentials of the theory by rendering ambiguous modifiers in the formal language of recursion.
{"title":"Algorithmic Semantics of Ambiguous Modifiers with the Type Theory of Acyclic Recursion","authors":"Roussanka Loukanova","doi":"10.1109/WI-IAT.2012.246","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.246","url":null,"abstract":"With his work on formal languages of recursion, Yiannis Moschovakis initiated development of a new approach to the mathematical notion of algorithm, beginning with work on the mathematics of algorithms in 1994. One of the most exciting potentials of the approach is for applications to computational semantics of artificial and natural languages. In particular, the typed version of theory of a cyclic recursion and its language reveal crucial properties of semantic concepts such as meaning and synonymy, from computational perspective. This paper is a brief introduction to Moschovakis' Type Theory of A cyclic Recursion and its system of reduction rules from the perspective of its applications to semantics of a class of modifiers. The formal language of a cyclic recursion and its theory have potentials for applications to algorithmic semantics of natural and artificial languages. The paper demonstrates the potentials of the theory by rendering ambiguous modifiers in the formal language of recursion.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"87 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":"114999584","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}
Personalized recommendation is, according to the user's interest characteristics and purchasing behavior, to recommend information and goods to users in which they may be interested. With the rapid development of Internet technology, we have entered the era of information explosion, where huge amounts of information are presented at the same time. On one hand, it is difficult for the user to discover information in which he is most interested, on the other hand, general users experience difficult in obtaining information which very few people browse. In order to extract information in which the user is interested from a massive amount of data, we propose a personalized recommendation algorithm based on approximating the singular value decomposition (SVD) in this paper. SVD is a powerful technique for dimensionality reduction. However, due to its expensive computational requirements and weak performance for large sparse matrices, it has been considered inappropriate for practical applications involving massive data. Finally, we present an empirical study to compare the prediction accuracy of our proposed algorithm with that of Drineas's LINEARTIMESVD algorithm and the standard SVD algorithm on the Movie Lens dataset, and show that our method has the best prediction quality.
{"title":"A Personalized Recommendation Algorithm Based on Approximating the Singular Value Decomposition (ApproSVD)","authors":"Xun Zhou, Jing He, Guangyan Huang, Yanchun Zhang","doi":"10.1109/WI-IAT.2012.225","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.225","url":null,"abstract":"Personalized recommendation is, according to the user's interest characteristics and purchasing behavior, to recommend information and goods to users in which they may be interested. With the rapid development of Internet technology, we have entered the era of information explosion, where huge amounts of information are presented at the same time. On one hand, it is difficult for the user to discover information in which he is most interested, on the other hand, general users experience difficult in obtaining information which very few people browse. In order to extract information in which the user is interested from a massive amount of data, we propose a personalized recommendation algorithm based on approximating the singular value decomposition (SVD) in this paper. SVD is a powerful technique for dimensionality reduction. However, due to its expensive computational requirements and weak performance for large sparse matrices, it has been considered inappropriate for practical applications involving massive data. Finally, we present an empirical study to compare the prediction accuracy of our proposed algorithm with that of Drineas's LINEARTIMESVD algorithm and the standard SVD algorithm on the Movie Lens dataset, and show that our method has the best prediction quality.","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":"114665107","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}
Knowledge management systems help organizations to track organizational knowledge such as human, structural or relational capital. The relational capital of organizations tends to include intangible factors and, consequently, it is not always possible to determine this value from traditional business oriented accounting systems. The problem addressed in this research is: how to analyze this capital to achieve a network evaluation metric. Thus, answer the question: "What is the value of your network?". This research has been developed in the SNARE ("Social Network Analysis and Reengineering Environment") project that involves engineering artifacts to extract, analyze and monitor the value of social networks. The SNARE-RCO (short for "Relational Capital of Organizations") model allows us to define and evaluate the relational capital of organizations. it combines techniques derived from social network analysis with aspects of organizational assessment, including also human and structural capital. This paper reviews SNARE-RCO's main elements, which are applied to compute the relational capital value of three social networks, namely: (1) Telecommunications operator, (2) School, and (3) Collaborative social platform.
{"title":"What is the Value of Your Network?","authors":"Alexandre Barão, A. Silva","doi":"10.1109/WI-IAT.2012.267","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.267","url":null,"abstract":"Knowledge management systems help organizations to track organizational knowledge such as human, structural or relational capital. The relational capital of organizations tends to include intangible factors and, consequently, it is not always possible to determine this value from traditional business oriented accounting systems. The problem addressed in this research is: how to analyze this capital to achieve a network evaluation metric. Thus, answer the question: \"What is the value of your network?\". This research has been developed in the SNARE (\"Social Network Analysis and Reengineering Environment\") project that involves engineering artifacts to extract, analyze and monitor the value of social networks. The SNARE-RCO (short for \"Relational Capital of Organizations\") model allows us to define and evaluate the relational capital of organizations. it combines techniques derived from social network analysis with aspects of organizational assessment, including also human and structural capital. This paper reviews SNARE-RCO's main elements, which are applied to compute the relational capital value of three social networks, namely: (1) Telecommunications operator, (2) School, and (3) Collaborative social platform.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"8 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":"134227994","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}
Eugene Santos, Qi Gu, Eunice E. Santos, John Korah
An important task of modeling complex social behaviors is to observe and understand individual/group beliefs and attitudes. These beliefs, however, are not stable and may change multiple times as people gain additional information/perceptions from various external sources, which in turn, may affect their subsequent behavior. To detect and track such influential sources is challenging, as they are often invisible to the public due to a variety of reasons -- private communications, what one randomly reads or hears, and implicit social hierarchies, to name a few. Existing approaches usually focus on detecting distribution variations in behavioral data, but overlook the underlying reason for the variation. In this paper, we present a novel approach that models the belief change over time caused by hidden sources, taking into consideration the evolution of their impact patterns. Specifically, a finite fusion model is defined to encode the latent parameters that characterize the distribution of the hidden sources and their impact weights. We compare our work with two general mixture models, namely Gaussian Mixture Model and Mixture Bayesian Network. Experiments on both synthetic data and a real-world scenario show that our approach is effective on detecting and tracking hidden sources and outperforms existing methods.
{"title":"Hidden Source Behavior Change Tracking and Detection","authors":"Eugene Santos, Qi Gu, Eunice E. Santos, John Korah","doi":"10.1109/WI-IAT.2012.137","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.137","url":null,"abstract":"An important task of modeling complex social behaviors is to observe and understand individual/group beliefs and attitudes. These beliefs, however, are not stable and may change multiple times as people gain additional information/perceptions from various external sources, which in turn, may affect their subsequent behavior. To detect and track such influential sources is challenging, as they are often invisible to the public due to a variety of reasons -- private communications, what one randomly reads or hears, and implicit social hierarchies, to name a few. Existing approaches usually focus on detecting distribution variations in behavioral data, but overlook the underlying reason for the variation. In this paper, we present a novel approach that models the belief change over time caused by hidden sources, taking into consideration the evolution of their impact patterns. Specifically, a finite fusion model is defined to encode the latent parameters that characterize the distribution of the hidden sources and their impact weights. We compare our work with two general mixture models, namely Gaussian Mixture Model and Mixture Bayesian Network. Experiments on both synthetic data and a real-world scenario show that our approach is effective on detecting and tracking hidden sources and outperforms existing methods.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"45 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":"133300746","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}
Florent Garcin, Kai Zhou, B. Faltings, Vincent Schickel
Because of the abundance of news on the web, news recommendation is an important problem. We compare three approaches for personalized news recommendation: collaborative filtering at the level of news items, content-based system recommending items with similar topics, and a hybrid technique. We observe that recommending items according to the topic profile of the current browsing session seems to give poor results. Although news articles change frequently and thus data about their popularity is sparse, collaborative filtering applied to individual articles provides the best results.
{"title":"Personalized News Recommendation Based on Collaborative Filtering","authors":"Florent Garcin, Kai Zhou, B. Faltings, Vincent Schickel","doi":"10.1109/WI-IAT.2012.95","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.95","url":null,"abstract":"Because of the abundance of news on the web, news recommendation is an important problem. We compare three approaches for personalized news recommendation: collaborative filtering at the level of news items, content-based system recommending items with similar topics, and a hybrid technique. We observe that recommending items according to the topic profile of the current browsing session seems to give poor results. Although news articles change frequently and thus data about their popularity is sparse, collaborative filtering applied to individual articles provides the best results.","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":"122068297","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}
A. Molina, Jangwon Choi, Jorge Gaete-Villegas, In-Young Ko
The proactive and spontaneous delivery of Web services for users on the move can lead to the depletion of their cognitive resources, affecting the normal processes of their physical activities. This is due to the competition for limited cognitive resources between the human-computer interactions required by Web services and the users' physical activities. This paper introduces a mechanism for binding and scheduling Web services based on an assessment of this competition for users on the move. The proposed approach is built on two theories from cognitive psychology. This mechanism is realized by a descriptive model of activities and Web services which is enriched with a cognitive layer. A computational model uses this description to assess the degree of the demand for cognitive resources by both the physical activities and the Web services. Additionally, a Web services coordination mechanism based on this level of demand, the principle of progressive disclosure, and the temporal concurrency of Web services ensures less cognitively taxing Web service compositions.
{"title":"Cognitive Resource-Aware Adaptive Web Service Binding and Scheduling","authors":"A. Molina, Jangwon Choi, Jorge Gaete-Villegas, In-Young Ko","doi":"10.1109/WI-IAT.2012.189","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.189","url":null,"abstract":"The proactive and spontaneous delivery of Web services for users on the move can lead to the depletion of their cognitive resources, affecting the normal processes of their physical activities. This is due to the competition for limited cognitive resources between the human-computer interactions required by Web services and the users' physical activities. This paper introduces a mechanism for binding and scheduling Web services based on an assessment of this competition for users on the move. The proposed approach is built on two theories from cognitive psychology. This mechanism is realized by a descriptive model of activities and Web services which is enriched with a cognitive layer. A computational model uses this description to assess the degree of the demand for cognitive resources by both the physical activities and the Web services. Additionally, a Web services coordination mechanism based on this level of demand, the principle of progressive disclosure, and the temporal concurrency of Web services ensures less cognitively taxing Web service compositions.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"76 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":"125919591","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}
Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers' tastes. However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommendations. To solve this problem, we propose a simple and effective method, called serendipitous personalized ranking. The experimental results demonstrate that our method significantly improves both accuracy and serendipity for top-N recommendation compared to traditional personalized ranking methods in various settings.
{"title":"Serendipitous Personalized Ranking for Top-N Recommendation","authors":"Qiuxia Lu, Tianqi Chen, Weinan Zhang, Diyi Yang, Yong Yu","doi":"10.1109/WI-IAT.2012.135","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.135","url":null,"abstract":"Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers' tastes. However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommendations. To solve this problem, we propose a simple and effective method, called serendipitous personalized ranking. The experimental results demonstrate that our method significantly improves both accuracy and serendipity for top-N recommendation compared to traditional personalized ranking methods in various settings.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"66 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":"124209952","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}
Uncovering user interest plays an important role to develop personalized systems in various fields including the Web and pervasive computing. In particular, online social networks (OSNs) are being spotlighted as the means to understand users' social behavior out of abundant online social information. In this paper, we explore a computational method of inferring user interest in Facebook by combining the degree of familiarity and topic similarity with social neighbors based on social correlation phenomenon. By conducting a question-naire survey, we demonstrate that our proposed method increases the accuracy of inference by 12.4% compared to existing methods which do not consider the latent topic structure implied in social contents.
{"title":"Inferring User Interest Using Familiarity and Topic Similarity with Social Neighbors in Facebook","authors":"Da-Seon Ahn, Taehun Kim, S. Hyun, Dongman Lee","doi":"10.1109/WI-IAT.2012.64","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.64","url":null,"abstract":"Uncovering user interest plays an important role to develop personalized systems in various fields including the Web and pervasive computing. In particular, online social networks (OSNs) are being spotlighted as the means to understand users' social behavior out of abundant online social information. In this paper, we explore a computational method of inferring user interest in Facebook by combining the degree of familiarity and topic similarity with social neighbors based on social correlation phenomenon. By conducting a question-naire survey, we demonstrate that our proposed method increases the accuracy of inference by 12.4% compared to existing methods which do not consider the latent topic structure implied in social contents.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"1 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":"130262826","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：