Methanias Colaço Júnior

Data Warehousing in an Industrial Software Development Environment

Data quality is one of the bases for effective data mining. Flexible, consistent and extensible data storage is one of the requirements for effective data analysis. For more than 15 years, researchers in the database and decision making world have been studying the construction of data repositories for data analysis. Named data warehouses, these repositories are historical databases, which are separated both logically and physically from the organization production environment and designed to store data gathered from this environment. Data warehousing also includes data selection, integration and organization approaches to make data easily accessible to the decision making process. Based on our previous experience with data warehousing for mining software repositories, this paper presents a Data Warehousing Approach for software development data analysis.

Mining Software Change History in an Industrial Environment

Version control systems are among the type of repositories that are frequently explored as sources of software change history. They can be mined to identify associations between software module modifications. This information is useful to support software modification activities, indicating to software engineers which modules are usually modified together during software maintenance or evolution. Previous works published on the subject focused on mining associations from open source software projects. This article presents the use of association mining in an industrial environment. The study was set up as a formal experiment and studied 18 systems developed in a large Brazilian beverage company. The results show that the precision of the rules obtained in this environment are even higher than its counterpart obtained in open source projects. This suggests that this approach is very useful in this type of environment.

A systematic mapping study on mining software repositories

Background: Software repositories provide large amount of data encompassing software changes throughout its evolution. Those repositories can be effectively used to extract and analyze pertinent information and derive conclusions related to the software history or its current snapshot. Objective: This work aims to investigate recent studies on Mining Software Repositories (MSR) approaches collecting evidences about software analysis goals (purpose, focus, and object of analysis), data sources, evaluation methods, tools, and how the area is evolving. Method: A systematic mapping study was performed to identify and analyze research on mining software repositories by analyzing five editions of Working Conference on Mining Software Repositories -- the main conference on this area. Results: MSR approaches have been used for many different goals, mainly for comprehension of defects, analysis of the contribution and behavior of developers, and software evolution comprehension. Besides, some gaps were identified with respect to their goals, focus, and data source type (e.g. lack of usage of comments to identify smells, refactoring, and issues of software quality). Regarding the evaluation method, our analysis pointed out to an extensive usage of some types of empirical evaluation. Conclusion: Studies of the MSR have focused on different goals, however there are still many research opportunities to be explored and issues associated with MSR that should be considered.

Approaches for Generating Empathy: A Systematic Mapping

Empathy plays an important role in social interactions, such an effective teaching-learning process in a teacher-student relationship, and company-client or employee-customer relationship to retain potential clients and provide them with greater satisfaction. Increasingly, people are using technology to support their interactions, especially when the interlocutors are geographically distant from one another. This has a negative impact on the empathic capacity of individuals. In the Computer Science, there are different approaches, techniques and mechanisms to promote empathy in social or human-computer interactions. Therefore, this article presents a systematic mapping to identify and systematize the approaches, techniques and mechanisms used in computing to promote empathy. As a result, we have identified existing approaches (e.g. collaborative learning environment, virtual and robotics agents, and collaborative/affective games) to promote empathy, the main areas involved (e.g. human-computer interaction, artificial intelligence, robotics, and collaborative systems), the top researchers and their affiliations who are potential contributors to future research and, finally, the growth status of this line of research.

Smartphone-based outlier detection: a complex event processing approach for driving behavior detection

The majority of fatal car crashes are caused by reckless driving. With the sophistication of vehicle instrumentation, reckless maneuvers, such as abrupt turns, acceleration, and deceleration, can now be accurately detected by analyzing data related to the driver-vehicle interactions. Such analysis usually requires very specific in-vehicle hardware and infrastructure sensors (e.g. loop detectors and radars), which can be costly. Hence, in this paper, we investigated if off-the-shelf smartphones can be used to online detect and classify the driver’s behavior in near real-time. To do so, we first modeled and performed an intrinsic evaluation to assess the performance of three outlier detection algorithms formulated as a data stream processing network which receives as input and processes data streams of smartphone and vehicle sensors. Next, we implemented a novel scoring mechanism based on online outlier detection to quantitatively evaluate drivers’ maneuvers as either cautious or reckless. Thus, we adapted a data mining mechanism which takes into account a sensor’s data rates and power to determine driver behavior in the scoring process. Finally, as the intrinsic evaluation does not necessarily reveal how well an algorithm will perform in a real-world scenario, we evaluated the algorithm that achieved the best result in a real-world case study to assess drivers’ driving behavior. Our results indicate that the algorithm performs quickly and accurately; the algorithm classifies driver behavior with 95.45% accuracy. Moreover, such results are obtained within 100 milliseconds of processing time on average.

An Approach to Improve the Empathy of Text Interactions in Collaborative Systems

In general, research on the effects of computer-mediation on collaborative work has concentrated mainly on social-psychological factors such as deindividuation, attitude polarization, social presence and politeness tactics. A new approach for that is the use of NeuroLinguistic theory to determine what is the Preferred Representational cognitive System (PRS) of collaborators. Internal mental processes such as problem solving, memory, and language consist of visual, auditory and kinesthetic representations. An important question on this matter is: Classify the representation most used (PRS) on moment of the text interactions can increase empathy? This position paper presents a psychometrically-based neurolinguistic proposal to enhance the empathy in the Computer-Mediated Communication.

Mining on Line General Opinions About Sustainability of Hotels: A Systematic Literature Mapping

Context: Nowadays, people do not only navigate, but also contribute content to the Internet. Thoughts and opinions are written on rating sites, forums, social networks, blogs and other media. Such opinions constitute a valuable source of information for companies, governs and consumers, but it would be humanly impossible to analyze and locate the opinions in those assessments, due to the large volume and different origins of the data. For this, approaches and techniques of opinion mining in texts are used. Objective: To identify and characterize the techniques used for mining data in public opinion repositories regarding hotels, since the opinion mining area has offered necessary subsidies for decision-making related to hotel management. Besides, to identify, specifically, studies that investigated the opinions about the sustainability of hotels. Method: A systematic mapping was performed to characterize the research area. Results: It was identified that, among the main approaches, 31% of the works found use only data mining, while 55% exclusively use machine learning techniques, and 14% both. Conclusion: The most relevant studies in such research lines adopt machine learning algorithms such as Naive Bayes, SVM, LDA, decision tree, besides aspect-based techniques and SentiWordNet lexicon dictionaries. There are still opportunities to explore opinion mining solutions in online hotel reviews, mainly by taking into consideration aspects related to sustainable practices and sustainability levels practiced by each hotel.

Summary Report of Experimental Analysis of Stemming Algorithms Applied to Judicial Jurisprudence

Stemming algorithms are commonly used during textual preprocessing phase in order to reduce data dimensionality. However, this reduction presents different efficacy levels depending on the domain it is applied. Hence, this work is an experimental analysis about the dimensionality reduction by stemming a veracious base of judicial jurisprudence formed by four subsets of documents. With such document base, it is necessary to adopt techniques that increase the efficiency of storage and search for such information, otherwise there is a loss of both computing resources and access to justice, as stakeholders may not find the document they need to plead their rights. The results show that, among the stemming algorithms analyzed, the RSLP algorithm was the most effective in terms of dimensionality reduction in the four collections studied.

A Initial Experimental Evaluation of the NeuroMessenger: A Collaborative Tool to Improve the Empathy of Text Interactions

Empathy plays an important role in social interactions, for example, in effective teaching-learning processes in teacher-student relationships, and in the company-client or employee-customer relationships, retaining potential partners and providing them with greater satisfaction. In parallel, the Computer-Mediated Communication (CMC) support people in their interactions, especially when the interlocutors are geographically distant from one another. In CMC, there are several approaches to promote empathy in social or human- computer interactions. However, for this type of communication, a little explored mechanism to gain empathy is the use of the theory of Neurolinguistics that presents the possibility of developing a Preferred Representation System (PRS) for cognition in humans. In this context, this paper presents an experimental evaluation of the NeuroMessenger, a collaborative messenger library that uses Neurolinguistics, Psychometry and Text Mining to promote empathy among interlocutors, from the PRS identification and suggestion of textual matching. The results showed that the performance with the use of NeuroMessenger, in favor of empathy, was higher, as well as there was an evidence statistically significant of the difference between the distribution of grades in the empathy evaluation,in favor of NeuroMessenger. Despite the results are satisfactory, more research on textual matching to gain empathy is needed.

Experimental Analysis of Stemming on Jurisprudential Documents Retrieval

Stemming algorithms are commonly used during textual preprocessing phase in order to reduce data dimensionality. However, this reduction presents different efficacy levels depending on the domain that it is applied to. Thus, for instance, there are reports in the literature that show the effect of stemming when applied to dictionaries or textual bases of news. On the other hand, we have not found any studies analyzing the impact of radicalization on Brazilian judicial jurisprudence, composed of decisions handed down by the judiciary, a fundamental instrument for law professionals to play their role. Thus, this work presents two complete experiments, showing the results obtained through the analysis and evaluation of the stemmers applied on real jurisprudential documents, originating from the Court of Justice of the State of Sergipe. In the first experiment, the results showed that, among the analyzed algorithms, the RSLP (Removedor de Sufixos da Lingua Portuguesa) possessed the greatest capacity of dimensionality reduction of the data. In the second one, through the evaluation of the stemming algorithms on the legal documents retrieval, the RSLP-S (Removedor de Sufixos da Lingua Portuguesa Singular) and UniNE (University of Neuchâtel), less aggressive stemmers, presented the best cost-benefit ratio, since they reduced the dimensionality of the data and increased the effectiveness of the information retrieval evaluation metrics in one of analyzed collections.