Computational approaches to subjectivity and sentiment analysis: Present and envisaged methods and applications

Recent years have witnessed a surge of interest in computational methods for affect, ranging from opinion mining, to subjectivity detection, to sentiment and emotion analysis. This article presents a brief overview of the latest trends in the field and describes the manner in which the articles contained in the special issue contribute to the advancement of the area. Finally, we comment on the current challenges and envisaged developments of the subjectivity and sentiment analysis fields, as well as their application to other Natural Language Processing tasks and related domains.

Applying model-driven engineering to the development of Rich Internet Applications for Business Intelligence

Business Intelligence (BI) applications have been gradually ported to the Web in search of a global platform for the consumption and publication of data and services. On the Internet, apart from techniques for data/knowledge management, BI Web applications need interfaces with a high level of interoperability (similar to the traditional desktop interfaces) for the visualisation of data/knowledge. In some cases, this has been provided by Rich Internet Applications (RIA). The development of these BI RIAs is a process traditionally performed manually and, given the complexity of the final application, it is a process which might be prone to errors. The application of model-driven engineering techniques can reduce the cost of development and maintenance (in terms of time and resources) of these applications, as they demonstrated by other types of Web applications. In the light of these issues, the paper introduces the Sm4RIA-B methodology, i.e., a model-driven methodology for the development of RIA as BI Web applications. In order to overcome the limitations of RIA regarding knowledge management from the Web, this paper also presents a new RIA platform for BI, called RI@BI, which extends the functionalities of traditional RIAs by means of Semantic Web technologies and B2B techniques. Finally, we evaluate the whole approach on a case study—the development of a social network site for an enterprise project manager.

Design and development of agent-based procurement system to enhance business intelligence

The purpose of this research is to propose a procurement system across other disciplines and retrieved information with relevant parties so as to have a better co-ordination between supply and demand sides. This paper demonstrates how to analyze the data with an agent-based procurement system (APS) to re-engineer and improve the existing procurement process. The intelligence agents take the responsibility of searching the potential suppliers, negotiation with the short-listed suppliers and evaluating the performance of suppliers based on the selection criteria with mathematical model. Manufacturing firms and trading companies spend more than half of their sales dollar in the purchase of raw material and components. Efficient data collection with high accuracy is one of the key success factors to generate quality procurement which is to purchasing right material at right quality from right suppliers. In general, the enterprises spend a significant amount of resources on data collection and storage, but too little on facilitating data analysis and sharing. To validate the feasibility of the approach, a case study on a manufacturing small and medium-sized enterprise (SME) has been conducted. APS supports the data and information analyzing technique to facilitate the decision making such that the agent can enhance the negotiation and suppler evaluation efficiency by saving time and cost.

Semantic sentiment analysis of Twitter

Sentiment analysis over Twitter offer organisations a fast and effective way to monitor the publics' feelings towards their brand, business, directors, etc. A wide range of features and methods for training sentiment classifiers for Twitter datasets have been researched in recent years with varying results. In this paper, we introduce a novel approach of adding semantics as additional features into the training set for sentiment analysis. For each extracted entity (e.g. iPhone) from tweets, we add its semantic concept (e.g. Apple product) as an additional feature, and measure the correlation of the representative concept with negative/positive sentiment. We apply this approach to predict sentiment for three different Twitter datasets. Our results show an average increase of F harmonic accuracy score for identifying both negative and positive sentiment of around 6.5% and 4.8% over the baselines of unigrams and part-of-speech features respectively. We also compare against an approach based on sentiment-bearing topic analysis, and find that semantic features produce better Recall and F score when classifying negative sentiment, and better Precision with lower Recall and F score in positive sentiment classification.

Social media and sentiment in bioenergy consultation

he push to widen participation in public consultation suggests social media as an additional mechanism through which to engage the public. Bioenergy companies need to build their capacity to communicate in these new media and to monitor the attitudes of the public and opposition organisations towards energy development projects. Design/methodology/approach This short paper outlines the planning issues bioenergy developments face and the main methods of communication used in the public consultation process in the UK. The potential role of social media in communication with stakeholders is identified. The capacity of sentiment analysis to mine opinions from social media is summarised, and illustrated using a sample of tweets containing the term ‘bioenergy’ Findings Social media have the potential to improve information flows between stakeholders and developers. Sentiment analysis is a viable Purpose The push to widen participation in public consultation suggests social media as an additional mechanism through which to engage the public. Bioenergy companies need to build their capacity to communicate in these new media and to monitor the attitudes of the public and opposition organisations towards energy development projects. Design/methodology/approach This short paper outlines the planning issues bioenergy developments face and the main methods of communication used in the public consultation process in the UK. The potential role of social media in communication with stakeholders is identified. The capacity of sentiment analysis to mine opinions from social media is summarised, and illustrated using a sample of tweets containing the term ‘bioenergy’ Findings Social media have the potential to improve information flows between stakeholders and developers. Sentiment analysis is a viable methodology, which bioenergy companies should be using to measure public opinion in the consultation process. Preliminary analysis shows promising results. Research limitations/implications Analysis is preliminary and based on a small dataset. It is intended only to illustrate the potential of sentiment analysis and not to draw general conclusions about the bioenergy sector. Originality/value Opinion mining, though established in marketing and political analysis, is not yet systematically applied as a planning consultation tool. This is a missed opportunity.

Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

Business intelligence em sistemas de apoio à gestão de frotas: Análise de Tecnologias e metodologias

O objecto de estudo desta tese de mestrado surgiu da necessidade de dar resposta a uma proposta para uma solução de business intelligence a pedido de um cliente da empresa onde até à data me encontro a desempenhar funções de analista programador júnior. O projecto consistiu na realização de um sistema de monitorização de eventos e análise de operações, portanto um sistema integrado de gestão de frotas com módulo de business intelligence. Durante o decurso deste projecto foi necessário analisar metodologias de desenvolvimento, aprender novas linguagens, ferramentas, como C#, JasperReport, visual studio, Microsoft SQL Server entre outros. ABSTRACT: Business Intelligence applied to fleet management systems - Technologies and Methodologies Analysis. The object of study of this master's thesis was the necessity of responding to a proposal for a business intelligence solution at the request of a client company where so far I find the duties of junior programmer. The project consisted of a system event monitoring and analysis of operations, so an integrated fleet management with integrated business intelligence. During the course of this project was necessary to analyze development methodologies, learn new languages, tools such as C #, JasperReports, visual studio, Microsoft Sql Server and others.

Augmenting analytical CRM strategies with social BI

Large communities built around social media on the Internet offer an opportunity to augment analytical customer relationship management (CRM) strategies. The purpose of this paper is to provide direction to advance the conceptual design of business intelligence (BI) systems for implementing CRM strategies. After introducing social CRM and social BI as emerging fields of research, the authors match CRM strategies with a re-engineered conceptual data model of Facebook in order to illustrate the strategic value of these data. Subsequently, the authors design a multi-dimensional data model for social BI and demonstrate its applicability by designing management reports in a retail scenario. Building on the service blueprinting framework, the authors propose a structured research agenda for the emerging field of social BI.

Corporate document mining for technology intelligence: An analysis of needs, utilization and possibilities

This paper focuses on document data, one of the most significant sources for technology intelligence. To help organisations use their knowledge in documents effectively, this research aims to identify what organizations really want from documents and what might be possible to obtain from them. The research involves a literature review, a series of in-depth/on-site interviews and a descriptive analysis of document mining applications. The output of the research includes: a document mining framework; an analysis of the current condition of document mining in technology-based organisations together with their future requirements; and guidelines for introducing document mining into an organisation along with a discussion on the practical issues that are faced by users. Copyright © 2011 Inderscience Enterprises Ltd.

Towards a situation-awareness-driven design of operational business intelligence & analytics systems

With the swamping and timeliness of data in the organizational context, the decision maker’s choice of an appropriate decision alternative in a given situation is defied. In particular, operational actors are facing the challenge to meet business-critical decisions in a short time and at high frequency. The construct of Situation Awareness (SA) has been established in cognitive psychology as a valid basis for understanding the behavior and decision making of human beings in complex and dynamic systems. SA gives decision makers the possibility to make informed, time-critical decisions and thereby improve the performance of the respective business process. This research paper leverages SA as starting point for a design science project for Operational Business Intelligence and Analytics systems and suggests a first version of design principles.

A lesson in business: cost-effectiveness analysis of a novel financial incentive intervention for increasing physical activity in the workplace

Background: Recently both the UK and US governments have advocated the use of financial incentives to encourage healthier lifestyle choices but evidence for the cost-effectiveness of such interventions is lacking. Our aim was to perform a cost-effectiveness analysis (CEA) of a quasi-experimental trial, exploring the use of financial incentives to increase employee physical activity levels, from a healthcare and employer’s perspective.

Methods: Employees used a ‘loyalty card’ to objectively monitor their physical activity at work over 12 weeks. The Incentive Group (n=199) collected points and received rewards for minutes of physical activity completed. The No Incentive Group (n=207) self-monitored their physical activity only. Quality of life (QOL) and absenteeism were assessed at baseline and 6 months follow-up. QOL scores were also converted into productivity estimates using a validated algorithm. The additional costs of the Incentive Group were divided by the additional quality adjusted life years (QALYs) or productivity gained to calculate incremental cost effectiveness ratios (ICERs). Cost-effectiveness acceptability curves (CEACs) and population expected value of perfect information (EVPI) was used to characterize and value the uncertainty in our estimates.

Results: The Incentive Group performed more physical activity over 12 weeks and by 6 months had achieved greater gains in QOL and productivity, although these mean differences were not statistically significant. The ICERs were £2,900/QALY and £2,700 per percentage increase in overall employee productivity. Whilst the confidence intervals surrounding these ICERs were wide, CEACs showed a high chance of the intervention being cost-effective at low willingness-to-pay (WTP) thresholds.

Conclusions: The Physical Activity Loyalty card (PAL) scheme is potentially cost-effective from both a healthcare and employer’s perspective but further research is warranted to reduce uncertainty in our results. It is based on a sustainable “business model” which should become more cost-effective as it is delivered to more participants and can be adapted to suit other health behaviors and settings. This comes at a time when both UK and US governments are encouraging business involvement in tackling public health challenges.

Using Brain Data for Sentiment Analysis

We present the results of exploratory experiments using lexical valence extracted from brain using electroencephalography (EEG) for sentiment analysis. We selected 78 English words (36 for training and 42 for testing), presented as stimuli to 3 English native speakers. EEG signals were recorded from the subjects while they performed a mental imaging task for each word stimulus. Wavelet decomposition was employed to extract EEG features from the time-frequency domain. The extracted features were used as inputs to a sparse multinomial logistic regression (SMLR) classifier for valence classification, after univariate ANOVA feature selection. After mapping EEG signals to sentiment valences, we exploited the lexical polarity extracted from brain data for the prediction of the valence of 12 sentences taken from the SemEval-2007 shared task, and compared it against existing lexical resources.

Implementação de uma solução open source de Business Intelligence com metodologia Ágil

A importância dos sistemas de data warehousing e business intelligence é cada vez mais pronunciada, no sentido de dotar as organizações com a capacidade de guardar, explorar e produzir informação de valor acrescido para os seus processos de tomada de decisão. Esta realidade é claramente aplicável aos sectores da administração pública portuguesa e, muito em particular, aos organismos com responsabilidades centrais no Ministério da Saúde. No caso dos Serviços Partilhados do Ministério da Saúde (SPMS), que tem como missão prover o SNS de sistemas centrais de business intelligence, o apelo dos seus clientes, para que possam contar com capacidades analíticas nos seus sistemas centrais, tem sido sentido de forma muito acentuada. Todavia, é notório que, tanto os custos, como a complexidade, de grande parte destes projetos têm representado uma séria ameaça à sua adoção e sucesso. Por um lado, a administração pública tem recebido um forte encorajamento para integrar e adotar soluções de natureza open source (modelo de licenciamento gratuito), para os seus projetos de sistemas de informação. Por outro lado, temos vindo a assistir a uma vaga de aceitação generalizada de novas metodologias de desenvolvimento de projetos informáticos, nomeadamente no que diz respeito às metodologias Agéis, que se assumem como mais flexíveis, menos formais e com maior grau de sucesso. No sentido de averiguar da aplicabilidade do open source e das metodologias Ágeis aos sistemas de business intelligence, este trabalho documenta a implementação de um projeto organizacional para a SPMS, com recurso a ferramentas open source de licenciamento gratuito e através de uma metodologia de desenvolvimento de natureza Ágil.

Business Intelligence para apoio à gestão das listas de inscritos para cirurgia em Portugal continental

Em Portugal Continental a problemática das listas de inscritos para cirurgia e os seus tempos de espera são matérias que preocupam a sociedade portuguesa desde o início da década de noventa, do século XX. Atualmente as ferramentas de business intelligence ganham cada vez maior importância nas organizações inseridas num contexto mais complexo, competitivo e que exige respostas rápidas, adequadas e em constante mudança. O projeto desenvolvido consiste na implementação de uma aplicação de business intelligence, na Unidade Central de Gestão de Inscritos para Cirurgia, sedeada na Administração Central do Sistema de Saúde, I.P., que apoie a gestão das listas de inscritos para cirurgia de forma mais atempada, com maior qualidade e rigor, e com benefícios inquestionáveis para os utentes. Este projeto visa a monitorização de indicadores basilares; melhoria do controlo do desempenho dos hospitais; comparação entre os valores estabelecidos para determinados indicadores e os desvios verificados; simulação do impacto de algumas medidas, na lista de inscritos para cirurgia, antes da sua implementação; e facultar informação que permita adequar, a todo o momento, a oferta à procura, em determinadas patologias cirúrgicas. Os objetivos do projeto, definidos à priori, foram concretizados na sua totalidade, tendo sido a aplicação concluída com sucesso. Sugere-se, como ações futuras, acrescer novos indicadores e mais dimensões de análise à aplicação desenvolvida no âmbito deste projeto, alargando a capacidade de análise da Unidade Central de Gestão de Inscritos para Cirurgia, com inerente aumento da sua competência de gestão da Lista de Inscritos para Cirurgia em Portugal Continental.