Stanley Loh

• Doctor in Computer Science
• Lutheran University of Brazil

Este artigo apresenta o SisRecCol – Sistema de Recomendação para Apoio à Colaboração. O sistema oferece ferramentas que tem por finalidade apoiar o processo de aprendizagem colaborativa. O sistema segue a perspectiva sócio-interacionista de Vygotsky, procurando a partir da identificação dos perfis interagentes, realizar recomendações que possam aux...

This chapter presents a study of integration of traditional CRM systems with new social networking technologies available on the Web, such as Twitter, blogs, and communities, showing a set of the best practices on the use of these technologies to improve business relationships with customers. The authors present a set of best practices with guidanc...

The modern business landscape demands that organizations maintain an online presence to network with their customers and investors. Therefore, understanding the link between social media and e-business is an important first step in cultivating these internet-based relationships. Organizations and Social Networking: Utilizing Social Media to Engage...

Research on digital media has mostly paid attention to users’ demographics, motivations, and efficacy, but with increasingly popular web tools like social media, it is important to study more stable psychological characteristics such as users’ personality traits, as they may significantly affect how people use the Web to communicate and socialize....

In this chapter, we develop a theoretical framework that explains how blogs can be categorized based on audiences’ perceptions and how bloggers use different strategies to shape or shift their audiences’ perceptions and increase the persuasiveness of their messages. We posit that bloggers use two distinguishable communication strategies: (a) develo...

Consumers are increasingly consuming, participating, contributing, and sharing different types of online content. This is influencing the marketing activities traditionally controlled and performed by companies. The aim of this chapter is to conceptualize the activities consumers perform in social media. Social media denote content created by indiv...

O artigo apresenta as características do Jornalismo Semântico, uma visão que busca descrever tecnologias que auxiliam a descrição e consequentemente a recuperação eficiente de informações jornalísticas na Web por seres humanos, viabilizando a sua manipulação por outros dispositivos computacionais. Pretende-se com isso contribuir para a conscientiza...

A Internet é um grande repositório de informações e conhecimento. Para a Gestão do Conhecimento, seja dentro de empresas ou para pessoas individualmente, esta é uma das maneiras mais fáceis de encontrar conhecimento explícito. Entretanto, as informações disponibilizadas na Internet não são padronizadas ou geridas por um órgão fiscalizador. Sendo as...

This chapter presents a software tool that helps the Competitive Intelligence process by collecting and analyzing texts published on the Internet. The goal is to automatically analyze indicators of the sentiment present in texts about a certain theme, whether positive or negative. The sentiment analysis is made through a probabilistic process over...

In multi-agent recommender systems, agents are able to generate recommendations according to the preferences of the customer. However, in some domains, specific knowledge is required in order to compose a recommendation and this knowledge may be not available for the agent. In these cases, agents need to communicate with other agents in the communi...

This paper describes the Personal Tour recommender system that helps customers to find best travel packages according to their preferences. Personal Tour is based on the paradigm of the Distributed Artificial Intelligence and a customer recommendation request is divided into partial recommendations that are handled by different agents. Experiments...

This paper presents the study of a technique for implementation of organization control systems. The proposed protocol is based on MASPA and is able to perform searches in the agent network, finding the agent capable of performing the task with a low cost. Experiments were conducted to validate the presented protocol.

This chapter describes the Personal Tour: a multi-agent recommender system designed to help users to find best travel packages according to their preferences. Personal Tour is based on the collaboration of multiple agents exchanging information stored in their local knowledge bases. Based on the paradigm of the Distributed Artificial Intelligence,...

In the context of Internet, there are many tools that allow sharing knowledge. Examples of these tools are Web chats. However it is possible to use Web chats in a more effective way. In this sense, this paper presents a system that analyzes the themes discussed in a chat room and then recommends information sources according to the context of the d...

This is a voice QA system for Brazilian Portuguese that performs speech recognition, text processing, database access and speech synthesis for consulting both structured and unstructured datasets. This system provides multi-modal communication and has the potential to help users with disabilities to access relevant information, and may help to sign...

COMUNICA is a voice QA system for Brazilian Portuguese with search capabilities for consulting both structured and unstructured datasets. One of the goals of this work is to help address digital inclusion by providing an alternative way to accessing written information, which users can employ regardless of available computational resources or compu...

Information Visualization is a field of computer graphics which aims to present information graphically, allowing users to better understand a great amount of information. It also allows identifying standards, or even detecting new information which, at first, was not possible to be perceived due to its complex representation. This study briefly de...

In many situations, related to some types of systems or organizations’ tasks, it is necessary to identify people with similar profiles. In the case of a collaborative recommender system, items to be recommended are those associated to similar users. Another example, in the academic environment, is to identify new members to be part of a research gr...

This paper presents investigations on representing user's profiles with information extracted from their sci-entific publications. The work assumes that scientific papers written by users can be used to represent user's interest or expertise and that these representations can be used to find similar users. The goal is to support similarity evaluati...

One of the main topics in IT Portfolio Management, according to IT Governance models, is to plan and control information systems that are aligned with the company mission and objectives. The goal of the IT Portfolio Planning is to define which information systems are necessary and with which priority. In general, planning methodologies trace direct...

With the growing publishing of news in the Web, techniques are necessary to describe news content in order to facilitate future retrieval. The use of tags is one of the most popular alternatives to describe Web content. However, in general, tags are manually selected. This work presents the study of different automatic techniques to identify or sel...

This work investigates the use of keywords and classes to represent user's profiles in order to improve a content-based recommender system. The techniques were implemented and tested in a recommender system for a website that gathers commercial ads. Ads are posted by individuals and contain a title and a textual description. Profiles are created an...

This paper presents an approach that identifies Loc ation Indicators related to geographical locations, by analyzing tex ts of news published in the Web. The goal is to semi-automatically create Gazet teers with the identified relations and then perform geo-referencing of news. Location Indicators include non-geographical entities that are dynamic...

This chapter introduces a technique to cluster textual documents using concepts. Document clustering is a technique capable of organizing large amounts of documents in clusters of related information, which helps the localization of relevant information. Traditional document clustering techniques use words to represent the contents of the documents...

The goal of this chapter is to present an approach to mine texts through the analysis of higher level characteristics (called “concepts’), minimizing the vocabulary problem and the effort necessary to extract useful information. Instead of applying text mining techniques on terms or keywords labeling or extracted from texts, the discovery process w...

A categorização e organização do conteúdo através de tags (Folksonomia) têm se tornado popular na web como resultado ao surgimento de sites que privilegiam a colaboração. Trabalhos recentes têm demonstrado que as tags são úteis para categorizar informações de forma geral, sendo no entanto menos eficientes na indicação de seu conteúdo específico. Pa...

This work describes a Text Mining technique which trying to identifying experts using information available in a digital library. A technique used trying to assign each author to concepts presents in a domain ontology. Each concept represents an expertise area. The results of an experiment are showed. The possible advantages obtained are discussed.

O presente artigo relata a utilização de funcionalidades e características de um sistema multiagente em um sistema de recomendação chamado SisRecAC. Este sistema descobre e recomenda artigos científicos baseados nos próprios documentos armazenados pelos usuários da ferramenta. Os agentes autônomos adicionados ao sistema possibilitarão automatizar a...

This chapter investigates different aspects in the construction of a domain ontology to a content-based recommender system. The recommender systems suggests textual electronic documents from a Digital Library, based on documents read by the users and based on textual messages posted in electronic discussions through a web chat. The domain ontology...

This chapter introduces a technique to cluster textual documents using concepts. Document clustering is a technique capable of organizing large amounts of documents in clusters of related information, which helps the localization of relevant information. Traditional document clustering techniques use words to represent the contents of the documents...

Este artigo apresenta um sistema para recomendação de dietas alimentares que utiliza a técnica de Raciocínio Baseado em Casos (RBC). O sistema é aplicado ao domínio da especialidade médica de nutrição, sendo que os casos são representados por pacientes. Ao longo do trabalho, são apresentadas as estratégias para a definição dos casos e do método de...

This paper presents a context-aware text summarizer based on ontologies intended to be used for adapting information to mobile devices. The system generates summaries from texts according to the profile of the user and the context where he/she is at the moment. Context is determined by spatial and temporal localization. Ontologies are used to allow...

This paper presents SisRecCol system. The system offers tools which aims to support collabora- tive learning processes. The system follows Vygotskys socio-interactionist theory, identifying user's profiles to produce recommendations that can assist the learning process. Recommendations are produced from the users behavioral analysis on a web chat a...

Resumo. O presente trabalho tem como objetivo apresentar diferentes técnicas de recomendação para usuários de Bibliotecas Digitais. As técnicas implementadas visam buscar uma distinção de tipos de usuários com o objetivo de realizar recomendações de maneira mais eficiente, um experimento sobre a influência que recomendações provenientes de um usuár...

[This paper is in portuguese] This paper presents a knowledge discovery process performed over texts, using a technique for analyzing time sequences. The technique was tested in medical records of patients admitted in a psychiatric hospital. Each time sequence is the set of records of one patient, chronologically sorted, representing evolution of t...

The present work presents an algorithm to identify users profile using their publications list. With the results it is possible to observe the profiles evolution through time in temporal graphs. These graphs show the users interest areas while he was inserted in the academy. The areas are shown with different intensity according to the moment. Resu...

[full-text in portuguese] http://www.lume.ufrgs.br/bitstream/handle/10183/7800/000557182.pdf?sequence=1

According to Nonaka and Takeuchi (1995), the majority of the organizational knowledge comes from interactions between people. People tend to reuse solutions from other persons in order to gain productivity.

Business Intelligence (BI) can benefit greatly from the bulk of knowledge that stays hidden in the large amount of textual information existing in the organizational environment. Text Mining (TM) is a technology that provides the support to extract patterns from texts. After interpreting these patterns, a business analyst can reach useful insights...

Information about the external environment and organizational processes are among the most worthwhile input for business intelligence (BI). Nowadays, companies have plenty of information in structured or textual forms, either from external monitoring or from the corporative systems. In the last years, the structured part of this information stock h...

Internet enables the construction and sharing of knowledge without physical frontiers. Despite all the technologies available for online discussions, the knowledge shared through electronic media could be better utilized. Following the socio-interactionist theory of Vygotsky (1984), this paper presents the SisRecCol system, that analyzes the themes...

This paper presents a recommender system to support collaboration among people. The system provides a private chat room, where people can exchange textual messages. Analyzing the messages, the system discove rs the themes discussed and then it can help people by recommending complementary knowledge sources. Furthermore, chat sessions are stored and...

Este artigo descreve o desenvolvimento de uma ferramenta para a identificação automática da expertise em curriculos (curriculo vitae) no formato Lattes. Esta identificação se dá através da extração de informações do arquivo XML gerado pela Plataforma Lattes. Uma vez feita à extração, são utilizadas técnicas de Text Mining de forma a fazer a associa...

This paper presents how text mining techniques can be used to analyze an enterprise's external environment searching for competitors, related products and services, marketing strategies and customers' opinions. A case study, using the UNCTAD Electronic Trading Opportunities (ETO) System, is presented. The ETO system enables "Trade Points" and trade...

This work presents a Virtual Assistant (VA) whose main goal is to supply information for Websites users. AVA is a software system that interacts with persons through a Web browser, receiving textual questions and answering automatically without human intervention. The VA supplies information by looking for similar questions in a knowledge base and...

This work presents a software system for selective clipping of web information. The system allows users to register queries, expressing their information needs, and monitors information sources (Web sites), in order to find new information and to push it to the users. The difference from traditional Web clipping systems is that FastNews only retrie...

This work presents a recommender system that analyzes textual messages sent during a communication session in a private Web chat, identifies the context of each message and recommends items from a Digital Library. Recommendations are directly made to users in the chat screen and are decided by a software system through a proactive paradigm, without...

Resumo O objetivo do presente trabalho é investigar o processo de classificação de textos sobre mensagens de um chat na Web. As mensagens de chat possuem algumas particularidades como concisão, pouco cuidado com correções ortográficas e revisões, devido a serem escritas às pressas e geralmente por pessoas leigas. Neste trabalho, foram utilizados mé...

Internet enables the raising of Virtual Communities, where people can share knowledge without physical frontiers. Despite all the technologies available to support these communities, the knowledge shared among theirs members could be better utilized. One of these possibilities is to analyze the themes present in discussions of a community in order...

This paper describes a recommender system to support collaboration using open source technologies. The system consists on a WebChat that using text mining techniques identifies the subject of the messages and selects items from a digital library to recommend to the chat participants. The system allows knowledge exchange among members of virtual com...

Business Intelligence (BI) can benefit greatly from the bulk of knowledge that stays hidden in the large amount of textual information existing in the organizational environment. Text Mining (TM) is a technology that provides the support to extract patterns from texts. After interpreting these patterns, a business analyst can reach useful insights...

para encontrar páginas Web conforme palavras-chave fornecidas pelo usuário. Depois disto, o sistema gera resumos dos textos presentes nas páginas resultantes. Os resumos são guiados pelos usuários, que devem definir novas palavras-chave. O uso de resumos permite ao usuário ter uma visão detalhada das informações presentes nas páginas Web sem necess...

Resumo: Este artigo apresenta um software de apoio à Gestão de Competências, auxiliando na identificação das competências de indivíduos através da análise de textos contidos em currículos (curricula vitae). O software apresentado permite a análise de currículos de profissionais candidatos ou já atuantes numa organização, minimizando o esforço de bu...

This paper presents a Text Mining approach for discovering knowledge in texts to later construct decision support systems. Text mining can take advantage of knowledge stored in textual documents, reducing the effort for knowledge acquisition. The approach consists in performing a mining process on concepts present in texts instead of working with w...

This work presents a recommender system that helps travel agents in discovering options for customers , especially those who do not know where to go and what to do. The system analyzes textual messages exchanged between a travel agent and a customer through a private Web chat. Text mining techniques help discover interesting areas in the messages....

Within organizations, people learn through exchanging knowledge. This kind of task (named collaboration) is important for the organizational learning. Collaboration can be supported by Information Technology tools as chats, newsgroups, forums and e-mailing lists. However, this kind of support only enables message exchange, lacking to help people in...

This paper describes an e-commerce application build on the Electronic Trading Opportunities System. This system enables ‘Trade Points’ and trade related bodies to exchange information by e-mail. This environment offers an enormous trade potential and opportunities to small and medium enterprises, but its efficiency is limited since the amount of c...

4 Clínica Olivé Leite, Pelotas – RS 5 Universidade Católica de Pelotas (UCPEL) – Escola de Medicina 6 Agência Nacional de Vigilância Sanitária (ANVISA) – Gerência Geral de Medicamentos Genéricos Resumo. Este trabalho apresenta uma estratégia para descoberta de conhecimento em prontuários eletrônicos. Os prontuários contêm informações textuais sobre...

in Portuguese.

This paper describes an experience based on an e-business application build on the Electronic Trading Opportunities (ETO) System. The ETO system enables 'Trade Points' and trade related bodies to exchange trade information by e-mail. This environment could offer an enormous trade potential and opportunities to small and medium enterprises, but its...

This paper presents an approach for performing knowledge discovery in texts through qualitative and quantitative analyses of high-level textual characteristics. Instead of applying mining techniques on attribute values, terms or keywords extracted from texts, the discovery process works over conceptss identified in texts. Concepts represent real wo...

This work presents an approach for exploring knowledge available with people, using Text Mining technology. The knowledge may come from internal collaborators or from customers. To make the knowledge concrete in electronic ways, the approach acquires information through textual documents. Text Mining tools are then used to extract concepts present...

In Portuguese. p.125-147.

This paper presents an approach for knowledge discovery in texts extracted from the Web. Instead of analyzing words or attribute values, the approach is based on concepts, which are extracted from texts to be used as characteristicas in the mining processs. Statisitcal techniques are applied on concepts in order to find interesting patterns in conc...

Document in Portuguese.

Resumo Este artigo apresenta uma abordagem para recuperação semântica de documentos textuais disponíveis na Internet. As ferramentas propostas combinam duas técnicas principais: a expansão semântica e a lógica fuzzy (difusa). A expansão semântica analisa o contexto dos termos fornecidos como entrada e determina um conjunto maior de termos para o pr...

We present a knowledge discovery tool to help the information retrieval process. This tool, which we define as Hyperdictionary, is capable of acquiring and holding relationships among words to describe the context of some information-the knowledge about some subject. This knowledge is then used to retrieve information by contextual search in a docu...

This article present an automatic tool for requirement elicitation and its object-oriented diagrammatic specification through the use of human knowledge. It presents the knowledge bases manually developed as heuristic rules. The use of human knowledge differentiates this tool from existing CASE tools, that are only useful in the next steps to Requi...

[This paper is in portuguese] This work presents an approach that constructs automatic tools to help users in searching documents in Internet. Contextual use of the words is analyzed in order to eliminate ambiguities and to discover topics interesting to users. Through successive refinements on searches and with user’s feedback, the set of document...

Information Visualization is a field of graphic computing which aims to represent information graphically, allowing better understanding of a great amount of information. It also allows identifying standards, or even detecting new information which, at first, was not possible to be perceived due to its way of representation. This study briefly desc...

This work presents a strategy to identify interest/expertise areas of professionals from analyzing their curricula vitae. A text mining technique is used to analyze the texts in the curricula and compare keywords to concepts defined in a domain ontology. The paper shows how the structure of the curriculum may be used for that purpose. The main appl...

O presente trabalho procura minimizar os problemas relativos à busca de informações em Portais Corporativos com o uso de um assistente digital (AD). Um AD é uma ferramenta de auxílio ao usuário capaz de encontrar informações relacionadas a um assunto de maneira rápida, intuitiva e eficaz. Um AD interage com usuários humanos através de um navegador...

This paper presents a software system that automatically identifies expertise in personal curriculums, stored in the Lattes format. The identification is made through the extraction of textual information from XM L structures used in the Lattes format. Text mining techniques are used to classify the texts according to themes defined in a domain ont...

This paper presents an investigation on different methods for constructing domain ontologies for indexing documents and to identify interest areas of users in order to create profiles. In this context, an ontology is composed by a hierarchy of co ncepts and each concept has a vector of keywords with associated weights. We start from a predefined hi...

This work presents an analysis of a ortographic corrector forchat environments. To aid this corrections, it was used a combinat ion of metrics for a similarity function development. Some experiments ha d been made us- ing different databases for the reference dictionary. The r eference dictionary is composed by terms compared through the similarity...

Resumo. Este artigo descreve uma ferramenta que procura realizar a identificação automática das áreas de interesse de indivíduos a partir de seus currículos. Esta identificação é feita através da aplicação de técnicas de Descoberta de Conhecimento em Textos sobre as informações extraídas do arquivo XML gerado pela Plataforma Lattes. As técnicas uti...

A busca por consolidação das empresas para assegurar capital para novos investimentos e manter o nível de competitividade são os desafios tanto para investidores quanto para empreendedores. Na mesma proporção em que crescem os negócios, cresce também a necessidade de gerenciamento de serviços internos para sustentar a complexidade da estrutura e pr...