Leo Leppänen

Finding and expressing news from structured data

In the age of increasing floods of information, finding the news signals from the noise has become increasingly resource and time intensive for journalists. Generally, news media companies have the important role of filtering and explaining this flood of information to the public. However, with the increase in availability of data sources, human journalists are unable to catch and report on all the news. This limitation, coupled with the need for media companies to continuously provide value to news readers, calls for automated solutions, such as automatically generating news from data. In order to support the journalists and media companies, and to provide value to audiences, this work proposes approaches for automatically finding news or newsworthy events from structured data using statistical analysis. Utilizing a real natural language news generation system as a case study, we demonstrate the feasibility and benefits of automating those processes. In particular, the paper reveals that through automation of the news generation process, including the generation of textual news articles, a large amount of news can be expressed in digestible formats to audiences, at varying local levels, and in multiple languages. In addition, automation allows the audience to tailor or personalize the news they want to read. Results of this work thus support and broaden the news offering and experiences for both media companies and the public.

Towards Data-Driven Generation of Visualizations for Automatically Generated News Articles

A feature news story is often accompanied by illustrations and visuals. These visualizations can be, e.g., timelines, line charts, pie charts, or images. In this article, we present a largely data-driven and domain-independent approach for generating visualizations to accompany automatically generated news articles. We demonstrate the feasibility of our approach by applying it to statistical data on crime in Finland. The practical implementation demonstrates how the automatically generated visualizations provide additional information and interactivity to the news articles. We further illustrate how the approach presented is easily transferable to different domains with structured numerical datasets.

Computational thinking as an emergent learning trajectory of mathematics

In the 21st century, the skills of computational thinking complement those of traditional math teaching. In order to gain the knowledge required to teach these skills, a cohort of math teachers participated in an in-service training scheme conducted as a massive open online course (MOOC). This paper analyses the success of this training scheme and uses the results of the study to focus on the skills of computational thinking, and to explore how math teachers expect to integrate computing into the K-12 math syllabus. The coursework and feedback from the MOOC course indicate that they readily associate computational thinking with problem solving in math. In addition, some of the teachers are inspired by the new opportunities to be creative in their teaching. However, the set of programming concepts they refer to in their essays is insubstantial and unfocused, so these concepts are consolidated here to form a hypothetical learning trajectory for computational thinking.

Search of the Emotional Design Effect in Programming Revised

In this paper, we validate and extend previous findings on using emotional design in online learning materials by using a randomized controlled trial in the context of a partially-online university level programming course. For students who did not master the content beforehand, our results echo previous observations: emotional design material was not perceived more favourably, while materials’ perceived quality was correlated with learning outcomes. Emotionally designed material lead to better learning outcomes per unit of time, but it didn’t affect students navigation in the material.