Tag Archives: hackathon

Students try to predict potential collaborations at Hack Cambridge

Our first event of 2016 was attending Hack Cambridge, the University of Cambridge’s very own hackathon.

The popular music venue, the Corn Exchange, was repurposed to fit 400+ hackers along with 20+ sponsors.  This was the first event by this team of organisers. They did well to get so many sponsors and draw such a large crowd, including teams from Spain and Croatia. Such a large gathering of incredibly bright people from all over the UK and beyond. Seems that building apps is old school, rather a lot of the teams that I talked to were turning their hands to number crunching types of hacks. Got to admit, I didn’t understand what some people were telling me.  Felt like a bit of a wally.

wheres-wally

Where’s Wally?

However, we fear these first-time organisers have bitten off more than they could chew with such a large event. The single biggest issue was down to poor (almost non-existent) WiFi which caused some teams to head home, almost defeating the purpose of the event in the first place. Admittedly, this was an issue with the location.  The whole event felt chaotic and over subscribed. Sorry guys. Learn and iterate.

The team that stood out the most and won the Mendeley challenge was team Leev. They used the Mendeley API to retrieve papers devoted to biomedical disciplines (e.g. genomics, drug discovery and development, chemical similarity). Data from PubMed was sourced to complement Mendeley data so they could create co-authorship networks – graphs where every node represents an author and edges show co-authorship between two individuals. Through analysing the network topology, they were able to predict individuals who are important in their field, are able to bridge fields, as well as get a glimpse of how tight-knit is the field in general. Based on link prediction, they were trying to predict potential collaborations, hoping to benefit the research community.

They applied a number of methods from network science to solve the problem:

  • Louvain method for community detection and network clustering
  • Adamic-Adar index for predicting how the network will evolve and to suggest potential collaborators
  • HITS algorithm for calculating the “importance” of each collaborator

 

 

leer

Team Leev –  Dilyana Mincheva, Chi-Jui Wu and Aleksejs Sazonovs. 

Congratulations to team Leev and thanks to all the others who participated in this event. You can read about the other Mendeley hacks here:

 

Mendeley Sponsors a Hackathon.

Major league is an American concept and something that, according to Google, relates to professional sport.

So we weren’t too sure what to expect when we received an email from “Tim Fogarty – UK Commissioner at Major League Hacking “. What the hell?

Major League Hacking was created with a mission to:

“Major League Hacking’s mission is to spread the hacker ethos to every student on the planet; to cultivate communities where aspiring hackers have the opportunity to learn, build, and share their creations with the world.”

Every semester they run over 60 hackathons worldwide in the US, Canada, Mexico and now they can add the UK feather to their cap. This is a league and universities earn points for the number of students they send to a hackathon, those with the most points wins.

Mendeley was happy to sponsor the first UK event which was held in the Bloomberg Offices here in London. The event itself consisted of about 200 students from universities around the UK. Such a diverse bunch. We even had some students under the age of 16! The event kicked off early on Saturday morning with pitches from all sponsors. Each sponsor had 5 minutes to describe their product and set their challenge.  The challenge that we set out for the students was the “best use of the API”. As this was our first sponsorship of a hackathon then we were not so sure as to the uptake but we were surprised that we had 4 teams try and build using the Mendeley API.

So, why did we attend? As a company who has monthly hackathons then this was right up our street of continuous learning. It’s not about getting teams to use the Mendeley API, it’s an opportunity to meet and mentor passionate students in building innovative cool stuff. And they did not fail to innovate. We were blown away by what we seen. The full list of projects are described here but alas there can only be one winner.

The application that we decided to nominate as the winner was developed by Oxford students Taimur Abdaal and his 2 friends Lukas Koebis and Joshua Hannah.  They built an application that generates an interactive graph of collaborators based on an author search using first name only. The backend as built in Python, and the frontend using normal HTML5 and CSS3 with jQuery and d3.js.  Here are some screen shots.

Note: Click on the images for larger versions.

papertrail-landing-page

Landing Page – Paul Erdős

 

papertrail-kris-jack-result

Collaborators of Kris

 

This is a lovely example of building something fun and interactive using our API. To figure out an author’s collaborators they used our catalog search endpoint with the ‘author’ query parameter set to ‘kris’ e.g.

https://api.mendeley.com:443/search/catalog?author=kris

If you click on the nodes in the graph it then performs another author search using our catalog search.

The guys from Oxford have set a high bar for future hackers and we can’t wait to see what the next bunch do with our API.

If you have any hacks to share with us then we would love to see what you have done using our API. Get in touch api@mendeley.com.