Abstract
Linking an expert to his knowledge areas is still a challenging research problem. The task is usually divided into two steps: identifying the knowledge areas/topics in the text corpus and assign them to the experts. Common approaches for the expert profiling task are based on the Latent Dirichlet Allocation (LDA) algorithm. As a result, they require pre-defining the number of topics to be identified which is not ideal in most cases. Furthermore, LDA generates a list of independent topics without any kind of relationship between them. Expert profiles created using this kind of flat topic lists have been reported as highly redundant and many times either too specific or too general. In this paper we propose a methodology that addresses these limitations by creating hierarchical expert profiles, where the knowledge areas of a researcher are mapped along different granularity levels, from broad areas to more specific ones. For the purpose, we explore the rich structure and semantics of Heterogeneous Information Networks (HINs). Our strategy is divided into two parts. First, we introduce a novel algorithm that can fully use the rich content of an HIN to create a topical hierarchy, by discovering overlapping communities and ranking the nodes inside each community. We then present a strategy to map the knowledge areas of an expert along all the levels of the hierarchy, exploiting the information we have about the expert to obtain an hierarchical profile of topics. To test our proposed methodology, we used a computer science bibliographical dataset to create a star-schema HIN containing publications as star-nodes and authors, keywords and ISI fields as attribute-nodes. We use heterogeneous pointwise mutual information to demonstrate the quality and coherence of our created hierarchies. Furthermore, we use manually labelled data to serve as ground truth to evaluate our hierarchical expert profiles, showcasing how our strategy is capable of building accurate profiles. © 2018, Springer Nature Switzerland AG.

Abstract
Evaluating scientists based on their scientific production is often a controversial topic. Nevertheless, bibliometrics and algorithmic approaches can assist traditional peer review in numerous tasks, such as attributing research grants, deciding scientific committees, or choosing faculty promotions. Traditional bibliometrics focus on individual measures, disregarding the whole data (i.e., the whole network). Here we put forward OTARIOS, a graph-ranking method which combines multiple publication/citation criteria to rank authors. OTARIOS divides the original network in two subnetworks, insiders and outsiders, which is an adequate representation of citation networks with missing information. We evaluate OTARIOS on a set of five real networks, each with publications in distinct areas of Computer Science. When matching a metric’s produced ranking with best papers awards received, we observe that OTARIOS is >20 more accurate than traditional bibliometrics. We obtain the best results when OTARIOS considers (i) the author’s publication volume and publication recency, (ii) how recently his work is being cited by outsiders, and (iii) how recently his work is being cited by insiders and how individual he his. © 2019, Springer Nature Switzerland AG.

Abstract

Abstract

Abstract
The analysis of sentiments, emotions, and opinions in texts is increasingly important in the current digital world. The existing lexicons with emotional annotations for the Portuguese language are oriented to polarities, classifying words as positive, negative, or neutral. To identify the emotional load intended by the author, it is necessary to also categorize the emotions expressed by individual words. EmoSpell is an extension of a morphological analyzer with semantic annotations of the emotional value of words. It uses Jspell as the morphological analyzer and a new dictionary with emotional annotations. This dictionary incorporates the lexical base EMOTAIX. PT, which classifies words based on three different levels of emotions-global, specific, and intermediate. This paper describes the generation of the EmoSpell dictionary using three sources: the Jspell Portuguese dictionary and the lexical bases EMOTAIX. PT and SentiLex-PT. Additionally, this paper details the Web application and Web service that exploit this dictionary. It also presents a validation of the proposed approach using a corpus of student texts with different emotional loads. The validation compares the analyses provided by EmoSpell with the mentioned emotional lexical bases on the ability to recognize emotional words and extract the dominant emotion from a text.

Abstract
Learning to program is hard. Students need to remain motivated to keep practicing and to overcome their difficulties. Several approaches have been proposed to foster students’ motivation. As most people enjoy playing games of some kind and play on a regular basis, the use of games is one of the most widely spread approaches. However, taking full advantage of games to teach specific concepts of programming requires much effort. This paper presents Asura, a game-based assessment environment built on top of Mooshak that challenges students to code Software Agents (SAs) to play a game, allowing them to test the SAs against each others’ SAs and watch a movie of the test. Once the challenge development stage ends, teachers are able to organize game-like tournaments among SAs. One of the key features of Asura is that it provides a means to reduce the required effort of building game-based challenges up to that of creating traditional programming exercises. © José Carlos Paiva and José Paulo Leal.