News / Highlights / Colloquium
EPJ Data Science Highlight - How news outlets target audiences
- Details
- Published on 22 May 2019
The mass media is one of the social forces with the most active transformative power. However, news reach people unequally. Many factors shape the distribution and influence of news media coverage. Some of these factors are the geographic reach of newspapers (national versus regional newspapers), the direct targeting of specific sectors of the population, and/or the political ideology of the media outlet itself.
In a recent article in EPJ Data Science, Erick Elejalde, from the L3S Research Centre in Hannover, Germany, explains how their work helps to identify whether or not an outlet’s coverage deviates from the purely geographic influence to a more sophisticated behavior involving the weight of political and socioeconomic interests.
Read the post on the SpringerOpen blog.
EPJ Data Science Highlight - Offline biases in online platforms
- Details
- Published on 09 April 2019
Online booking platforms such as Airbnb or Uber present themselves as and strive to be inclusive, but there is an increasing amount of both anecdotal and scientific evidence of discriminatory behavior among their users. In a study published in EPJ Data Science, researchers at University College London set out to evaluate interaction patterns within Airbnb, in an effort to understand the extent to which offline human biases influence affects their users.
Read the guest post by Giacomo Livan, Licia Capra, Weihua Li and Victoria Koh on the SpringerOpen blog
EPJ Data Science Highlight - Using deep learning to “see” inside homes across the world
- Details
- Published on 18 February 2019
How much does someone's living room tell about how they live? Peeking into another person's life might be just part of natural human curiosity, but the answer to this question may provide insights in a wide range of aspects of human behavior. A new study published in EPJ Data Science uses the power of machine learning to explore patterns of home decors—and what they could tell about their owners—in popular accommodation website Airbnb.
See guest post by Clio Andris and Xi Liu originally published in the SpringerOpen blog
EPJ Data Science Highlight - Twitter’s tampered samples: Limitations of big data sampling in social media
- Details
- Published on 16 January 2019
Social networks are widely used as sources of data in computational social science studies, and so it is of particular importance to determine whether these datasets are bias-free. In EPJ Data Science, Jürgen Pfeffer, Katja Mayer and Fred Morstatter demonstrate how Twitter’s sampling mechanism is prone to manipulation that could influence how researchers, journalists, marketeers and policy analysts interpret their data.
(Guest post by Jürgen Pfeffer, Katja Mayer and Fred Morstatter, originally published in the SpringerOpen blog)
EPJ Data Science Highlight - Listening to the changes in the urban rhythm
- Details
- Published on 01 October 2018
Cities evolve and undergo constant re-organisation as their population grow. This evolving process makes cities resilient and adaptive but also poses a challenge to analyse urban phenomena. For a long time, there has been evidence that suggests temporal and spatial regularities in crime, but so far studies about this have been based on the assumption that cities are static. A new study published in EPJ Data Science takes these factors into consideration and analyses spatio-temporal variation in criminal occurrences.
(Guest post by Marcos Oliveira & Ronaldo Menezes, originally published on the SpringerOpen blog)
EPJ Data Science Highlight - A model to predict Airbnb distribution in cities
- Details
- Published on 19 September 2018
The distribution of Airbnb listings has been the topic of much discussion among citizens and policy-makers, particularly in major cities. In an article published in EPJ Data Science, Giovanni Quattrone and colleagues looked into the many factors determining the spacial penetration of Airbnb in urban centers and developed a model that aims to predict this distribution in other cities. Among others, the presence of creative communities emerges as an important factor in the adoption of the housing plaftform.
(Guest post by Giovanni Quatronne, originally published on the SpringerOpen blog)
EPJ Data Science Highlight - Controlling epidemics using mobile phone data
- Details
- Published on 26 June 2018
Mobile data can be (and has been) used to study a vast number of subjects related to human behavior. One of its potential applications is on epidemics, a complex field that is informed not only by healthcare, but also social interactions and human mobility. In this blog post, Stefania Rubrichi explains the context in which her team used a real mobile phone dataset in an attempt to better understand and tackle the spread of diseases. Their study was just published in the journal EPJ Data Science.
(Guest post by Stefania Rubrichi, originally published on the SpringerOpen blog)
EPJ Data Science Highlight - Academic performance and behavioral patterns
- Details
- Published on 27 April 2018
In an article just published in EPJ Data Science, Valentin Kassarnig, Sune Lehmann and Andreas Bjerre-Nielsen look into smartphone data of undergraduate students to assess factors influencing social behavior and educational performance.
(Guest post by Valentin Kassarnig, Sune Lehmann & Andreas Bjerre-Nielsen, originally published on the SpringerOpen blog)
EPJ Data Science Highlight - Discovering temporal regularities in retail customers’ shopping behaviour
- Details
- Published on 18 April 2018
Why do we buy certain items when we buy them? A new study published in EPJ Data Science analyzes personal retail data to extract a temporal purchasing profile, which is able to summarize whether and when a customer makes a purchase. Its results show that certain patterns and types of shoppers are detectable, which can be used both by customers to enable personalized services, and by the retail market chain for providing offers and discounts tailored to the individual shoppers personal temporal profile.
(Guest post by Riccardo Guidotti and Anna Monreale, originally published on the SpringerOpen blog)
EPJ Data Science Highlight – The science behind what makes a bestselling book
- Details
- Published on 10 April 2018
Books that are fiction, thrillers or mysteries, have high initial sales numbers and are released around Christmas are more likely to be bestsellers, according to a study published in EPJ Data Science
(This post was originally published on the SpringerOpen blog)
A team of researchers from Northeastern University, Boston, used a big data approach to investigate what makes a book successful. By evaluating data from the New York Times Bestseller Lists from 2008 to 2016, they developed a formula to predict if a book would be a bestseller.
