Sérgio Nunes

MediaViz: An Interactive Visualization Platform for Online Media Studies

In this paper, we present the tools of the MediaViz project, a work-in progress platform that aims to provide researchers, academics and professionals from the media field with a set of analytical and exploratory resources to answer high level and complex questions about the online media panorama, in an efficient, visual and interactive way. Our approach consists of aggregating and processing news data from multiple online sources, and provide programatic access to it through an Application Programming Interface (API). The visualization tools leverage the data provided by the API, allowing users to interact, explore and interrogate that information. Through the use of data visualization techniques, we aim to characterize the publication patterns of multiple online news sources by analyzing and comparing distinct dimensions. Dimensions of interest include the frequency and flow of publications and social shares throughout time, and the geographic coverage of online news outlets. We present some of the developed visualization tools and describe how they can offer meaningful insights by providing a birds-eye view of distinct characteristics of the online mediascape.

Propagating Fine-Grained Topic Labels in News Snippets

We propose an unsupervised method for propagating automatically extracted fine-grained topic labels among news items to improve their topic description for subsequent text classification procedure. This method compares vector representations of news items and assigns to each news item the label of its closest neighbour with a different topic label. Results obtained show that high precision can be achieved in propagating the top ranked topic label, and that 2-gram and 3-gram feature representations optimize the precision.

Telling Stories with Data Visualization

In this article we survey the historical background and development of information and data visualization, and an overview of the intersection of data visualization with storytelling applied to the field of data journalism, where it finds its most widespread use in narrative visualizations. We start by explaining why the mere act of visualization can be highly useful to readers, helping them discover patterns and comprehend information. Backed by historical references, we will describe how some of the first data visualizations were used to explain facts, understand certain events, and determine courses of action. We will then outline how storytelling and narrative techniques are being currently used with data visualization to leverage the power of visual expression. Our goal is to characterize storytelling with data as a vibrant and interesting field that current journalism practices employ to help readers understand and form opinions on complex facts. By presenting concepts like storytelling with data and data stories, we aim to spark interest in further research in the applications of data visualization and narrative.

ECIR 2018: Text2Story Workshop - Narrative Extraction from Texts

The 1st International Workshop on Narrative Extraction from Texts (Text2Story 2018) was held in conjunction with the 40th European Conference on Information Retrieval, ECIR 2018, Grenoble on the 26 th March 2018. The workshop aimed to help foster the collaboration of researchers on a wide range of multidisciplinary issues related to the text-to-narrativestructure. The program consisted of two keynote talks, six research presentations, a poster session and a slot for demo presentations. This report briefly summarizes the workshop. More information about the workshop is available at http://text2story18.inesctec.pt

A Survey on Automatic Detection of Hate Speech in Text

The scientific study of hate speech, from a computer science point of view, is recent. This survey organizes and describes the current state of the field, providing a structured overview of previous approaches, including core algorithms, methods, and main features used. This work also discusses the complexity of the concept of hate speech, defined in many platforms and contexts, and provides a unifying definition. This area has an unquestionable potential for societal impact, particularly in online communities and digital media platforms. The development and systematization of shared resources, such as guidelines, annotated datasets in multiple languages, and algorithms, is a crucial step in advancing the automatic detection of hate speech.