{"title":"Earth Computing","authors":"Brett Stalbaum","doi":"10.1145/2820426.2822356","DOIUrl":"https://doi.org/10.1145/2820426.2822356","url":null,"abstract":"Under the banner of \"Earth Computing,\" the walkingtools.net laboratory (UNIFESP/UCSD) is exploring how data extracted from landscapes (using tools such as Geographic Information Systems) may return to those landscapes in a literal way: through distributed computing and the property of \"data locality\" inherent in contemporary compute platforms such as Hadoop. Indeed, not only through data locality, but through solar power and the literal placement of compute power in the landscape itself, all as a way to explore new options for land art and performance art. In this workshop students will examine the construction of a solar powered compute station based on the Raspberry Pi platform. The focus will be on setting up and installing the hardware elements, as well as issues related to network connectivity and systems administration of a remote sensor/compute system. Finally, the workshop participants will imagine potential uses for and form critiques of discrete, remote computation with \"earth stations.\"","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129509347","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}
Humberto Lidio Antonelli, Renata Pontin de Mattos Fortes
{"title":"A Support for Developers Implement the Accessibility Guidelines Regarding to Web Menus","authors":"Humberto Lidio Antonelli, Renata Pontin de Mattos Fortes","doi":"10.1145/2820426.2820445","DOIUrl":"https://doi.org/10.1145/2820426.2820445","url":null,"abstract":"Web pages are composed of elements, such as menus that are responsible for assisting navigation on the website. However, many of the menus are not developed properly, which creates accessibility barriers and hinders access to the contents. This paper aims to present a method for creating accessible menus. Initially, we studied the different types of menus and the accessibility guidelines involving the creation of accessible menus. From the studies, we developed a meta-model that gave rise to AMenu language, where we included all the technical details regarding to accessibility. Then, we developed the AMeG tool to facilitate the use of language. Finally, we conducted a case study with developers, in order to verify the feasibility of the approach, arguing its efficiency and limitations. The results indicate a reduction in efforts to develop accessible web menus, since developers do not have to deal with technical details of accessibility.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130676516","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}
Fabrício Benevenuto, Matheus Araújo, Filipe Nunes Ribeiro
{"title":"Sentiment Analysis Methods for Social Media","authors":"Fabrício Benevenuto, Matheus Araújo, Filipe Nunes Ribeiro","doi":"10.1145/2820426.2820642","DOIUrl":"https://doi.org/10.1145/2820426.2820642","url":null,"abstract":"Sentiment Analysis became an important topic in the Web recently, especially regarding to Online Social Networks. Many applications are monitoring products and brands, and even important social events like political campaigns. A large number of Sentiment Analysis methods and techniques were proposed in the literature. This short course offers an introduction to explore this theme. First, we present an overview about sentiment analysis and it's popular applications. Next, we discuss main methods from literature. Finally, we compare these methods with each other highlighting advantages and limitations.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116187129","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}
{"title":"Toward a Scoring Schema to Rank Candidate Instances of Ontological Classes: Extracting Brazilian Portuguese Texts from the Web","authors":"Fabio Lima, L. Salvador","doi":"10.1145/2820426.2820465","DOIUrl":"https://doi.org/10.1145/2820426.2820465","url":null,"abstract":"With the emergence of Information Extraction Systems driven by ontologies, boosted by the Semantic Web, there is a need for the development of scoring schemas that enable the automatic classification of information. These schemas, even so little explored in the Portuguese language, provide measures used in the stage of classification of relevant instances to ontological classes. In this way, this paper presents: (i) a brief discussion about existing scoring measures based on PMI (Pointwise Mutual Information); (ii) new scoring measures based on PMI and Standard Deviation Calculation; and (iii) an evaluation of all discussed measures in the context of Brazilian Portuguese texts from the web.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132283641","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}
{"title":"The Impact of Structured Event Embeddings on Scalable Stock Forecasting Models","authors":"J. B. Nascimento, Marco Cristo","doi":"10.1145/2820426.2820467","DOIUrl":"https://doi.org/10.1145/2820426.2820467","url":null,"abstract":"According to the efficient market hypothesis, financial prices are unpredictable. However, meaningful advances have been achieved on anticipating market movements using machine learning techniques. In this work, we propose a novel method to represent the input for a stock price forecaster. The forecaster is able to predict stock prices from time series and additional information from web pages. Such information is extracted as structured events and represented in a compressed concept space. By using such representation with scalable forecasters, we reduced prediction error by about 10%, when compared to the traditional auto regressive models.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130039919","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}
Moisés H. R. Pereira, F. Pádua, A. Pereira, G. D. Silva, Fabrício Benevenuto
{"title":"Multimodal Sentiment Analysis for Automatic Estimation of Polarity Tension of TV News in TV Newscasts Videos","authors":"Moisés H. R. Pereira, F. Pádua, A. Pereira, G. D. Silva, Fabrício Benevenuto","doi":"10.1145/2820426.2820461","DOIUrl":"https://doi.org/10.1145/2820426.2820461","url":null,"abstract":"This paper presents a multimodal approach to perform content-based sentiment analysis in TV newscasts videos in order to assist in the automatic estimation of polarity tension of TV news. The proposed approach aims to contribute to the semiodiscoursive study relative to the construction of ethos of those TV shows. In order to achieve this goal, it is proposed the application of computational methods of state-of-the-art that, through the processing of newscasts' videos of interest, perform the automatic emotion recognition in facial expressions. Moreover, they extract modulations in the participants' speech (e.g., news anchors, reporters, among others) and apply sentiment analysis techniques in their text obtained from closed caption, therefore making possible to estimate the emotional tension level in the enunciation of the TV news. In order to evaluate the accuracy and the applicability of the system, we use an actual dataset composed by 358 videos from three Brazilian newscasts. The experimental results are promising, which indicate the potential of the approach to support the analysis of TV newscasts discourse.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129220752","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}
M. A. Domingues, Thais Emanuele Santos, Raíza Hanada, B. C. Cunha, S. O. Rezende, M. G. Pimentel
{"title":"A Platform for the Recommendation of Points of Interest in Brazilian Cities: Architecture and Case Study","authors":"M. A. Domingues, Thais Emanuele Santos, Raíza Hanada, B. C. Cunha, S. O. Rezende, M. G. Pimentel","doi":"10.1145/2820426.2820448","DOIUrl":"https://doi.org/10.1145/2820426.2820448","url":null,"abstract":"The tourism sector in Brazil has grown considerably in recent years. Despite this growth, the sector still presents several problems such as the lack of information in Portuguese and in other languages for Brazilian and foreign tourists. The absence of information about tourist sites and ordinary services also affects individuals when settling in a new city, as it is the case when freshman students move to a new city to start their studies in a college or university. In this work, we propose an innovative vision of a context-aware platform for recommending points of interest in Brazilian cities, designed with mechanisms for collecting data from the web, for extracting points of interest and background information, and for learning context-aware recommendation models. The platform is accessed by a mobile application. To validate our proposal, we ran a case study where freshman students used the platform during their first months in a new city.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126837241","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}
{"title":"A Proposal of Dynamic Content Search in aUbiquitous Tourist Guid","authors":"Thiago Silva Souza, C. Costa, R. Righi, S. Rigo","doi":"10.1145/2820426.2820462","DOIUrl":"https://doi.org/10.1145/2820426.2820462","url":null,"abstract":"The growth of tourism associated with the development of information and communication technologies have changed the way people do tourism, because tourists now have several support tools at all stages of tourism. However, most of them do not consider important aspects. For example, the generation of tourist guides dynamically from information available on the Web. In addition, the guides often lack information about small towns, regarding number of population and economic aspects. Considering this scenario, the objective of this work is to propose a ubiquitous tourism model, based on mobile devices, called Ataîru. The main contribution is to perform a dynamic search for tourist contents in open databases available on the Web, presenting the results based on concepts of ubiquitous computing such as context awareness and transparency to the user. We performed an evaluation based on scenarios to assess the model.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114435064","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}
{"title":"An Approach to Sentiment Analysis of Web Applications in Portuguese","authors":"R. Martins, A. Pereira, Fabrício Benevenuto","doi":"10.1145/2820426.2820446","DOIUrl":"https://doi.org/10.1145/2820426.2820446","url":null,"abstract":"Sentiment analysis has been applied in many contexts, including user reviews analysis on products and services, trends and financial market moods. Established methods for sentiment analysis present a behavior that varies according to the application and its lexical base, generating different results among them. In this paper, a new sentiment analysis technique called SentiPipe will be presented, which takes the best of a set of methods, generating a less sensitive analysis based context. For such, it was used a real Web database of financial market news in Portuguese to which was applied the new sentiment detection proposal. The results were promising, showing improvement in all metrics analyzed in relation to the methods individually applied.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114889774","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}
Alan Livio Vasconcelos Guedes, R. Azevedo, M. Moreno, L. Soares
{"title":"Specification of Multimodal Interactions in NCL","authors":"Alan Livio Vasconcelos Guedes, R. Azevedo, M. Moreno, L. Soares","doi":"10.1145/2820426.2820436","DOIUrl":"https://doi.org/10.1145/2820426.2820436","url":null,"abstract":"This paper proposes an approach to integrate multimodal events--both user-generated, e.g., audio recognizer, motion sensors; and user-consumed, e.g., speech synthesizer, haptic synthesizer--into programming languages for the declarative specification of multimedia applications. More precisely, it presents extensions to the NCL (Nested Context Language) multimedia language. NCL is the standard declarative language for the development of interactive applications for Brazilian Digital TV and an ITU-T Recommendation for IPTV services. NCL applications extended with the multimodal features are presented as results. Historically, Human-Computer Interaction research community has been focusing on user-generated modalities, through studies on the user interaction. On the other hand, Multimedia community has been focusing on output modalities, through studies on timing and multimedia processing. The proposals in this paper is an attempt to integrate concepts of both research communities in a unique high-level programming framework, which aims to assist the authoring of multimedia/multimodal applications.","PeriodicalId":224319,"journal":{"name":"Proceedings of the 21st Brazilian Symposium on Multimedia and the Web","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130004579","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}