Brazilian Symposium on Multimedia and the Web最新文献_第3页

Modeling and Inference Based on the Semantics of Monitoring of Human Vital Signs 基于语义的人体生命体征监测建模与推理

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664584

A. B. Bastos, I. G. S. Júnior, R. B. Neto

引用次数: 3

Catalog of Templates: An Approach for Documenting Families of Hypermedia Documents 模板目录:一种记录超媒体文档族的方法

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664560

R. C. M. Santos, Carlos de Salles Soares Neto, L. Soares

引用次数: 0

Analyzing the Topological Structure of the eBay Negotiations' Network eBay谈判网络的拓扑结构分析

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664566

C. M. França, Antonio A. Rocha, P. B. Velloso

{"title":"Analyzing the Topological Structure of the eBay Negotiations' Network","authors":"C. M. França, Antonio A. Rocha, P. B. Velloso","doi":"10.1145/2664551.2664566","DOIUrl":"https://doi.org/10.1145/2664551.2664566","url":null,"abstract":"The OSN's (On-line Social Networks) have reached an incredible popularity in modern Internet. Those systems have been present in the daily lives of countless people helping them to share personal experiences, expectations and opinions. So high popularity has made of such networks complex systems. To understand the operation and phenomena that occur in such networks, there are metrics and models that capture aspects of their structures. The purpose of this work is to understand the complex reality of eBay ecommerce network, their connections and the dynamics of its users. Data were collected using a script developed in this work, and it resulted in a database of approximately 87 million transactions and 15 million different dealer users. From these data, the characterization was made estimating network metrics, like dealer users' degree distribution, that gave us key insights about the eBay negotiation network. We found that there are users who bought/sold for more than 100.000 different persons. We also found that a user A interacted over 4.000 times with another user B in just 3 months. Those and other interesting results, such as average distance and feedbacks ratings, were obtained, analyzed and discussed in this work.","PeriodicalId":114454,"journal":{"name":"Brazilian Symposium on Multimedia and the Web","volume":"734 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116074929","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}

引用次数: 3

Combining Multiple Metadata Types in Movies Recommendation Using Ensemble Algorithms 集成算法在电影推荐中的多元数据组合

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664569

Bruno Souza Cabral, Renato Dompieri Beltrao, M. Manzato, F. Durão

引用次数: 5

Multi-Entity Polarity Analysis in Financial Documents 财务文件中的多主体极性分析

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664574

Javier Zambrano Ferreira, Josiane Rodrigues, Marco Cristo, D. Oliveira

{"title":"Multi-Entity Polarity Analysis in Financial Documents","authors":"Javier Zambrano Ferreira, Josiane Rodrigues, Marco Cristo, D. Oliveira","doi":"10.1145/2664551.2664574","DOIUrl":"https://doi.org/10.1145/2664551.2664574","url":null,"abstract":"The amount of information available in the Internet does not allow performing manual content analysis to identify information of interest. Thus automated analyses are used to identify information of interest, and one increasingly important approach is the polarity analysis. Polarity analysis is the classification of a text document in positive, negative, and neutral, according to a certain topic. This classification of information is particularly useful in the finance domain, where news about a company can affect the performance of its stocks. Although most of the methods in financial domain consider that the whole document is associated with a particular entity, this is not always the case. In fact, it is common that authors cite several entities in a single document and these entities are cited with different polarity. Accordingly, the objective of this paper was to study strategies for polarity detection in financial documents with multiple entities. Specifically, we studied methods based on learning of multiple models, one for each observed entity, using SVM classifiers. We evaluated models based on the partition of documents into fragments according to the entities they cite. We used several heuristics to segment documents based on shallow and deep natural language processing (NLP). We found that entity-specific models created by partitioning the document collection into segments outperformed the strategy based on the use of entire documents. We also observed that more complex segmentation using anaphora resolution was not able to outperform a low-cost approach, based on simple string matching.","PeriodicalId":114454,"journal":{"name":"Brazilian Symposium on Multimedia and the Web","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130703456","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}

引用次数: 9

Web of Things: Automatic Publishing and Configuration of Devices 物联网:设备的自动发布和配置

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664573

Nailton Vieira de Andrade, D. Bastos, Cássio V. S. Prazeres

引用次数: 6

A Topic Aware-based Approach to Maximize Social Influence 以主题意识为基础的最大化社会影响力的方法

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664571

Daniel Santos, A. Perkusich, H. Almeida

{"title":"A Topic Aware-based Approach to Maximize Social Influence","authors":"Daniel Santos, A. Perkusich, H. Almeida","doi":"10.1145/2664551.2664571","DOIUrl":"https://doi.org/10.1145/2664551.2664571","url":null,"abstract":"The use of social networks has shown great potential for information diffusion and formation of public opinion. One key problem that has attracted researchers interest is Topic-based Influence Maximization, that refers to finding a small set of users on a social network that have the ability to influence a substantial portion of users on a given topic. The proposed solutions, however, are not suitable for large-scale social networks and must incorporate mechanisms for determining social influence among users on each topic of interest. Consequently, for these approaches, it becomes difficult or even unfeasible to deal quickly and efficiently with constant changes in the structure of social networks. This problem is particularly relevant as the topics of interest of users and the social influence they exert on each other for every topic are considered together. In this work, it is proposed a scalable solution, that makes use of data mining over an information propagation log, in order to directly select the initial set of influential users on a particular topic without the need to incorporate a previous step for learning users social influence with regard to that topic. As an additional benefit, the targeted seed set also offers an approximation guarantee of the optimal solution. Finally, it is presented a design of experiments over a data set containing information propagation data from a real social network. As main results, we have found some evidences that the proposed solution maintains a trade-off between scalability and accuracy.","PeriodicalId":114454,"journal":{"name":"Brazilian Symposium on Multimedia and the Web","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114724489","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}

引用次数: 2

A Metadata-based Framework for Quality Attribute Degradation Analysis in Web Systems 基于元数据的Web系统质量属性退化分析框架

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664570

Felipe A. P. Pinto, U. Kulesza, Leo Silva, E. Guerra

引用次数: 0

Anatomy of a Semantic Context Interpreter with Real-time Events Notification Support 解析支持实时事件通知的语义上下文解释器

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664577

G. M. Maranhão, I. G. S. Júnior, R. B. Neto

引用次数: 6

A Comparison of SVM Versus Naive-Bayes Techniques for Sentiment Analysis in Tweets: A Case Study with the 2013 FIFA Confederations Cup 支持向量机与朴素贝叶斯技术在推文情感分析中的比较——以2013年国际足联联合会杯为例

Brazilian Symposium on Multimedia and the Web Pub Date : 2014-11-18 DOI: 10.1145/2664551.2664561

André Luiz Firmino Alves, C. Baptista, Anderson Almeida Firmino, Maxwell Guimarães de Oliveira, A. Paiva

引用次数: 47