Posted on

How do you avoid spending too much? Studies on buying behaviour have emphasized that one way to do that is to raise the “pain of paying”. This uncomfortable feeling that comes with paying differs across payment methods and influences our decision to buy. Using a credit card is associated with a lower “pain of paying” – and therefore higher levels of spending – than paying with cash. An increased pain of paying is like a “moral tax”, as researcher Dan Ariely calls it, because it makes us less inclined to make the purchase.

Similar to credit cards, online buying has been associated with a medium to low level of “pain” and stimulates spending. This raises the question how irresponsible online spending that causes debt could be reduced. In our research we study if highlighting the consequences of going ahead with the purchase increases the “pain of paying” and as a result helps people to control their online spending in a responsible way.

Want to learn more about our approach? Read the full story on the Think Forward blog at

Posted on

There have been a lot of developments in the last years in machine learning. One of the main developments of course has been deep learning, but now also generative adversarial networks are becoming more and more interesting.

In some of my presentations I have been using the following graph to model and explain the most common machine learning algorithms. There are many more variations, but if you are new to this field it may help you get a good overview of machine learning.

Feel free to re-use the image if you credit me as source.

Posted on

I’m happy to announce that my Think Forward research proposal has been accepted. In this study I will analyse the effects of financial warnings on irresponsible spending behaviour. The project will run until March 2018.

“The aim of the Think Forward Research Challenge is to explore how existing research into how consumers make financial decisions can be made directly relevant to the lives of consumers. This will have a substantial impact on actual tools that will help people make better financial decisions.”

Consumers may take financially irresponsible decisions by buying expensive products that they cannot really afford, letting short term temptation win over long-term goals, and creating “buyer remorse.” This is especially the case with online transactions, where there is less “pain of payment” during financial transactions. Dan Ariely discusses several mechanisms of how to increase self-control in these situations. One of the options he describes is to create “red buttons” or self-control contracts, helping buyers to identify potentially harmful purchases before they are made, and protecting themselves against harmful spending behavior.

Posted on

Why would decision makers attend these masterclasses?
To make informed business decisions on and around cognitive technologies, decision makers must understand the foundations, as well as the context, of these technologies.

What do we offer?
The IBM Benelux Center for Advanced Studies (CAS) teamed up with our long term collaborators in academia to deliver two 2-day masterclasses to educate decision makers about the technology. The first day of a masterclass will be at the university, covering the academic basics in an accessible way, while the second day is at IBM providing a more industrial angle of the topic.

The first masterclass, titled Foundations of Cognitive Computing, is delivered together with the Vrije Universiteit Amsterdam featuring renowned professors such Lora Aroyo, Guszti Eiben, and Frank van Harmelen (final list to be confirmed), but we will also have talks by IBM Research (Ken Barker), and demonstrations of past and present projects delivered locally by CAS. The preliminary dates for this Masterclass are 16-17 November 2017.

Topics covered (subject to change upon demand):

  • The past, present and future of Artificial Intelligence
  • Introduction to Cognitive Computing and Watson
  • How do Cognitive Systems learn?
  • Where is Watson now?
  • AI for the Masses (AI services in the cloud)
  • When AI Goes Bad (Ethics)
  • Demos and Corresponding Deep Dives

The second masterclass, titled The Internet of Everything and Everyone, is delivered with TU Delft, containing talks by prof. Geert-Jan Houben, dr. Alessandro Bozzon and several other researchers and students at the university, but also from IBM (John Cohn, Victor Sanchez, etc), CAS researchers and students. The date for for this masterclass are 7-8 December 2017.

Topics covered (subject to change upon demand):

  • Data collection for Cognitive systems:
    • big data,
    • sensor data,
    • human data
  • Solving real problems with IoT and with human computation
  • Data Science to connect machines and humans
  • Demos by students, faculty and IBM on how the technology can be used

What benefits can the masterclasses bring?
By gaining and understanding of what the technology is based on and what it can do, attendees can engage in deeper, more meaningful conversations about Cognitive, IoT, etc. They might become inspired to start projects using the technology, or perhaps the class can help them become convinced about the value a proposed IBM project.

Interested?  Contact us via, or via Zoltan Szlavik and Benjamin Timmermans directly.

Posted on

Our paper Computational Controversy has been accepted at the SocInfo 2017 conference!

Climate change, vaccination, abortion, Trump: Many topics are surrounded by fierce controversies. The nature of such heated debates and their elements have been studied extensively in the social science literature. More recently, various computational approaches to controversy analysis have appeared, using new data sources such as Wikipedia, which help us now better understand these phenomena. However, compared to what social sciences have discovered about such debates, the existing computational approaches mostly focus on just a few of the many important aspects around the concept of controversies. In order to link the two strands, we provide and evaluate here a controversy model that is both, rooted in the findings of the social science literature and at the same time strongly linked to computational methods. We show how this model can lead to computational controversy analytics that have full coverage over all the crucial aspects that make up a controversy.

The poster related to the paper

Reference to our paper

  title={Computational Controversy},
  author={Benjamin Timmermans, Tobias Kuhn, Kaspar Beelen, Lora Aroyo},
  journal={9th International Conference on Social Informatics (SocInfo) 2017},
Posted on

I like geographic data, and in recent years developed a simple tool to easily visualize all of my Google location history data in a single zoomable and interactive map. It converts your complete Google location history data for use in a Google Fusion Table. You can customize the visualization to your own preference in the map settings. In order to hide artifacts in the GPS data the code splits movement when locations are too far apart. You can see a screenshot of my map below, which visualises six years of location history data with 1.4 million points.



In order to visualize your own location history, download the code repository on github and follow these steps:

  • Download your location history in JSON format via Google Takeout
  • Extract the JSON file and configure its location in
  • Run using Python 2.7 and your location history will be transformed into a CSV file with connected coordinates
  • Create a new Fusion Table in Google Drive and upload your history.csv file
  • Go to the map tab to view your location history. Change the feature styles such as Line Color to an opacity of 5% to 10%
  • Change the map to terrain view to improve visibility. You can share the map via Tools -> Publish
Posted on

I published an update to our dataset of crowdsourced annotations on controversy aspects, as part of the ControCurator project.

Experimental Setup

We evaluated the controversy aspects through a crowdsourcing experiment using the CrowdFlower platform. The collected annotations from this experiment were evaluated using the CrowdTruth methodology for measuring the quality of the annotations, the annotators, and the annotated articles. The relevance of each of the aspects was collected by asking the annotators whether they applied to the main topic of a given newspaper article. For this, we used a collection of 5 048 The Guardian articles that were retrieved through the Guardian news API. In order to save cost and focus on the main topic of an article only the first two paragraphs of each article were used. In an initial pilot we used 100 articles to test the use of a five point likert-scale answers versus “yes/no/I don’t know” type answers, and additionally whether showing five comments would help annotators identify whether the topic in an article is controversial. In a second pilot we evaluated with the same dataset whether rephrasing of the aspects and adding the time-persistence would make the identification more clear.


The results of the first pilot showed that for both settings when showing the article comments the number of annotators that select “I don’t know” option is significantly smaller (p-value = 0.003). Additionally, we found that the “yes/no/I don’t know” setup always finished faster. Although this difference is not significant (p-value = 0.0519), it may indicate that annotators were more willing to perform this task. Based on this we conclude that the variant with comments and yes-no answers gave the best performance in terms of speed and annotation quality. The results of the second pilot showed the rephrasing of the questions improved the identification as the number of people that selected the “I don’t know” option dropped from 15% to 3% with p=0.0001.

In the main experiment 5048 articles were annotated by 1 659 annotators resulting in 31 888 annotations. The evaluation of the controversy aspects was a two-fold: first the Pearson correlation coefficients were measured in order to identify how strong an aspect correlated with controversy in each judgment. Second, linear regression was applied to learn the regression coefficient between all of the aspects combined and the controversy score for a judgment. This value indicates the weight of an aspect with respect to the other aspects. The emotion aspect of an article was found to be the strongest indicator for controversy using both measures, while the multitude of actors was the weakest. The openness was said to be present most in 70.9% of the annotations, was annotated with a majority in 73% of the articles, and was found to be the most clearly represented aspect.


This dataset is built and used for the following papers. Please cite them if you decide to use our work.

Benjamin Timmermans, Lora Aroyo, Tobias Kuhn, Kaspar Beelen, Evangelos Kanoulas, Bob van de Velde, Gerben van Eerten: ControCurator: Understanding Controversy Using Collective Intelligence. Collective Intelligence Conference 2017

  title={ControCurator: Human-Machine Framework For Identifying Controversy},
  author={Timmermans, Benjamin and Beelen, Kaspar and Aroyo, Lora and Kanoulas, Evangelos and Kuhn, Tobias and van de Velde, Bob and van Eerten, Gerben},
  journal={Collective Intelligence Conference},

Benjamin Timmermans, Kaspar Beelen, Lora Aroyo, Evangelos Kanoulas, Tobias Kuhn, Bob van de Velde, Gerben van Eerten: ControCurator: Human-Machine Framework For Identifying Controversy. ICT Open 2017

  title={ControCurator: Understanding Controversy Using Collective Intelligence},
  author={Timmermans, B and Aroyo, L and Kuhn, T and Beelen, K and Kanoulas, E and van de Velde, B},
  journal={ICT Open},
Posted on

On June 15-16 the Collective Intelligence conference took place at New York University. The CrowdTruth team was present with Lora Aroyo, Chris Welty and Benjamin Timmermans. Together with Anca Dumitrache and Oana Inel we published a total of six papers at the conference.


The first keynote was presented by Geoff Mulgan, CEO of NESTA. He set the context of the conference by stating that there is a problem with technological development, namely that it only takes knowledge out of society and does not put it back in. Also, he made it clear that many of the tools we see today like Google Maps are actually nothing more than companies that were bought and merged together. This combination of things is what creates the power. He also defined what the biggest trends are in collective intelligence: the observation e.g. citizen generated data on floods, predictive models e.g. fighting fires with data, memory e.g. what works centers on crime reduction, and judgement e.g. adaptive learning tool for schools. Though, there are a few issues with collective intelligence: Who pays for all of this? What skills are needed for CI? What are the design principles of CI? What are the centers of expertise? These are all not yet clear. However, what is clear is that there is a new field emerging through combining AI with CI: Intelligence Design. We used to think systems resolve this intelligence, but actually we need to steer and design it.

In a plenary session there was an interesting talk on public innovation by Thomas Kalil. He defined the value of concreteness as things that happen when particular people or organisations take some action in pursuit of a goal. These actions are more likely to affect change if you can articulate who would needs to do what. He said he would like to identify the current barriers to prediction markets and areas where governments could be a user and funder of collective intelligence. This can be achieved through connecting people that are working to solve similar problems locally, e.g. in local education. Then change can be driven realistically, by making clear who needs to do what. Though, it was noted also that people need to be willing and able for change to work.

Parallel Sessions

There were several interesting talks during the parallel sessions. Thomas Malone spoke about using contest webs to address the problem of global climate change. He claims that funding science can be both straightforward and challenging, for instance government policy does not always correctly address the need of a domain issues, and even conflicts of interest may exist. Also, fundamental research can be tough to convince the general public of its use, as it is not sexy. Digital entrepreneurship is furthermore something that is often overlooked. There are hard problems, and there are new ways of solving them. It is essential now to split the problems up into parts, solve each of them with AI, and combine them back together.

Chris Welty presented our work on Crowdsourcing Ambiguity Aware Ground Truth at Collective Intelligence 2017.

Also Mark Whiting presented his work on Daemo, a new crowdsourcing platform that has a self-governing marketplace. He stress the fact that crowdsourcing platforms are notoriously disconnected from user interests. His new platform has a user driven design, in order to get rid of the flaws that exist in for instance Amazon Mechanical Turk.

Plenary Talks

Daniel Weld from the University of Washington presented his work on argumentation support in crowdsourcing. Their work uses argumentation support in crowd tasks to allow workers to reconsider their answers based on the argumentation of others. They found this to significantly increase the annotation quality of the crowd. He also claimed that humans will always need to stay in the loop of machine intelligence, for instance to define what the crowd should work on. Through this, hybrid human-machine systems are predicted to become very powerful.

Hila Lifshitz-Assaf of NYU Stern School of Business gave an interesting talk on changing innovation processes. The process of innovation has changed from a lane inventor, to labs, to collaborative networks, and now into open innovation platforms. The main issue with this is that the best practices of innovation fail in the new environment. In standard research and development there is a clearly defined and selectively permeable, whereas with open innovation platforms this is not the case. Experts can participate from in and outside the organisation. It is like open innovation: managing undefined and constantly changing knowledge in which anyone can participate. For this to work, you have to change from being a problem solve to a solution seeker. It is a shift from thinking: The lab is my world, to the world is my lab. Still, problem formulation is key as you need to define the problems in ways that cross boundaries. The question always remains, what is really the problem?

Poster Sessions

In the poster sessions there were several interesting works presented, for instance work on real-time synchronous crowdsourcing using “human swarms” by Louis Rosenberg. Their work allows people to change their answers through the influence of the rest of the swarm of people. Another interesting poster was by Jie Ren of Fordham University, who presented a method for comparing the divergent thinking and creative performance of crowds compared to experts. We ourselves had a total of five posters covering both poster sessions, which were received well by the audience.

Posted on

On 9th of June we are organising a Coffee & Data event with the Amsterdam Data Science community. The topic is “How to deal with controversy, bias, quality and opinions on the Web” and will be organised in the context of the COMMIT ControCurator project. In this project VU and UvA computer scientists and humanities researchers investigate jointly the computational modeling of controversial issues on the Web, and explore its application within real use cases in existing organisational pipelines, e.g. Crowdynews and Netherlands Institute for Sound and Vision.

The Agenda is as follows:

09:00-09:10 Coffee

Introduction & Chair by Lora Aroyo, Full Professor at the Web & Media group (VU, Computer Science)

09:10 – 09:25: Gerben van Eerten – Crowdynews deploying ControCurator

09:25 – 09:40: Kaspar Beelen – Detecting Controversies in Online News Media (UvA, Faculty of Humanities)

09:40 – 09:50: Benjamin Timmermans – Understanding Controversy Using Collective Intelligence (VU, Computer Science)

09:50 – 10:00: Davide Ceolin – (VU, Computer Science)

10:00 – 10:15: Damian Trilling – (UvA, Faculty of Social and Behavioural Sciences)

10:15 – 10:30: Daan Oodijk (Blendle)

10:30 – 10:45: Andy Tanenbaum – “Unskewed polls” in 2012

10:45 – 11:00: Q&A Coffee

The event takes place at the Kerkzaal (HG-16A00) on the top floor of the VU Amsterdam main building.