Travel time prediction (TTP) is a key component of Intelligent Transportation Systems, with applications in traffic management, logistics, urban mobility, and passenger services. The literature offers diverse methods, from simple approaches to deep learning techniques. However, the lack of a clear and systematic organization hinders practical application and comparison. This paper proposes a comprehensive taxonomy of TTP models, based on a systematic literature review from 2019 to 2023. The models are grouped into three main categories: naive, traffic theory-based, and data-driven. Each category is subdivided by model nature, data requirements, predictive capacity, and applicability. This taxonomy is intended as a tool for researchers to select models, compare approaches, and integrate new techniques within a unified framework.

When users search the Web it is difficult to return information that is as complete as possible. Also many short texts, such as tweets, are not self-contained and need to be explained since understanding them requires additional knowledge or related facts. Recent research focuses on the context of the user, not on complementing the search results, seeking to return more specific information for the search. Unlike previous works, this research focuses on the context of the retrieved data, attempting to enrich the returned information by incorporating complementary facts that give context to the information requested by the user.

In recent years, the use of information systems has become increasingly important in organizations, generating vast amounts of heterogeneous data from various sources. Data Science encompasses data mining and process mining disciplines, among others, that allow the management, analysis, and discovery of valuable information from this data. However, these disciplines are often applied independently, over different datasets obtained from heterogeneous data sources which are not necessarily integrated, and thus can lead to partial views when analyzing the results. To address this issue, this research proposes a unified approach to data mining and process mining over process and organizational integrated data, which enables a comprehensive view of the daily operation of organizations for evidence-based decision making. In this paper we present a proposal for carrying out such integrated analysis, and a proof of concept prototype developed to support it. We also present an example of application with process and organizational data from a real university process.

This article analyses an original crime data set from Montevideo, Uruguay's capital city, in 2019. The data was collected from various sources: News Web Portals, for example El Observador, Teledoce, El País and MontevideoCOMM; mobile phone applications in which users report crimes such as CityCop; and Official Data from Home Office annual reports, that despite being an open data set, it is not easily consumable. Our main objective is to study the relationship between the perception of CitiCop users through reported crimes, media perception as presented in News Web Portals and Official Data which is of public domain. Geostatistical techniques are applied to analyse similarities and differences between the three perceptions previously described. Results show interesting coincidences and dissents.

Recommender Systems are valuable tools which suggest meaningful and useful items to users. In a previous research project, a real recommender system which offers personalized recommendations of items to health professionals and medical specialists in the context of Continuing Medical Education (CME) was designed and developed. Traceability helps recommender systems to generatejustifications about the criteria used for selecting the suggestions of items to the active user. This paper presents a novel approach for modelling traceability in recommender systems in the given context. The proposed approach shows how to use different levels of relationships between users to trace the origin of the recommendations. An important contribution of this research is to explain how to generalize the proposed model of traceability in recommender systems. In addition, an automated approach towards communicating the origin of the recommendations to the users is proposed.