My current research is focused on understanding the importance of network structure in network inference and human behaviour. I am interested on discovering latent and valuable knowledge from the interactions and attributes of online and offline users, especially in networks [see Google ScholarResearchGate].

[ 2018 ]

Towards Quantifying Sampling Bias in Network Inference.

Lisette Espín-NoboaClaudia Wagner, Fariba Karimi and Kristina Lerman.
In WWW ’18 Companion: The 2018 Web Conference Companion, April 23–27, 2018, Lyon, France. 
ACM, New York, NY, USA, 9 pages.
- LatinXinAI@NeurIPS2018: [abstractposter]

[ 2017 ]

JANUS: A Hypothesis-driven Bayesian Approach for Understanding Edge Formation in Attributed Multigraphs.

Lisette Espín-Noboa, Florian Lemmerich, Markus Strohmaier and Philipp Singer.
Applied Network Science, 2017.
[pdf] [code]

How Users Explore Ontologies on the Web: A Study of NCBO's BioPortal Usage Logs.

Simon Walk, Lisette Espín-NoboaDenis Helic, Markus Strohmaier and Mark A. Musen.
In Proceedings of 26th International World Wide Web Conference WWW'17

[ 2016 ]

A Hypotheses-driven Bayesian Approach for Understanding Edge Formation in Attributed Multigraphs.

Lisette Espín-Noboa, Florian Lemmerich, Markus Strohmaier and Philipp Singer.
In Proceedings of the 5th International Workshop on Complex Networks and their Applications. Milan, Italy, 2016 Nov 29.

Discovering and Characterizing Mobility Patterns in Urban Spaces: A Study of Manhattan Taxi Data.

Lisette Espín-Noboa, Florian Lemmerich, Philipp Singer and Markus Strohmaier.
In Proceedings of the 25th International Conference Companion on World Wide Web (pp. 537-542). International World Wide Web Conferences Steering Committee (WWW). Montreal, Canada, 2016 Apr 11.
[pdf] [slides]

[ 2015 ]

Understanding How Users Edit Ontologies: Comparing Hypotheses About Four Real-World Projects.

Simon Walk, Philipp Singer, Lisette Espín Noboa, Tania Tudorache, Mark A. Musen and Markus Strohmaier.
InThe Semantic Web (pp. 551-568). Springer International Publishing (ISWC). Betlehem, Pennsylvania, USA, 2015 Oct 11.

Characterizing Information Diets of Social Media Users

Juhi Kulshrestha, Muhammad Bilal Zafar, Lisette Espin Noboa , Krishna P. Gummadi, Saptarshi Ghosh.
InNinth International AAAI Conference on Web and Social Media (ICWSM). Oxford, UK, 2015 Apr 21.

[ 2014 ]

TTopic - Inferring Topical Context for Tweets, Hashtags and Trending Topics on Twitter

Today, millions of users are relying on Twitter to discover real-time content on their various topics of interest. However, since 271M active users post more than 500M tweets every day on Twitter, it is almost infeasible for individual users to discover important content on their topics of interest. Moreover, only 12.3% of tweets posted in Twitter contain meaningful information such as pass-along value messages and news, the rest are spam, self promotion, pointless babble and conversational tweets, and it is very difficult for users to discover interesting topical information from out of this large amount of non-topical content. 

This work is a novel methodology for inferring topical context of individual tweets. Note that inferring the topic of a tweet is especially challenging, due to the very small size of tweets (limited to 140 characters) and bad textual quality of the posts as a result of frequent use of abbreviations, non-formal language, conventions, etc. Hence, TTopic does not rely only on the content of the tweet, but also the topical attributes of the users who discuss the context of the tweet. The key idea is that if multiple users having similar topical attributes / expertise (e.g., politicians, or musicians, or physicists) discuss a certain common context, that context is very likely to be related to the common topic of expertise of these users. 

This work was part of my Master's Research at the Max Planck Institute for Software Systems.
[pdf] [slides] [demo]
demo in maintenance