Program

Tuesday, April 24th, 2018

Session 1 (1:40pm-3:00pm)

1:40 - 1:45 Opening
 

1:45 - 2:30 Keynote Talk: Social Data for Social Good and a Biased Perspective on Research Impact - Alexandra Olteanu (IBM Research)



Abstract: The ever-growing datasets of user activity traces promise to offer captivating insights into human phenomena.  Yet, these datasets are more than just an observational tool.  The insights derived from them are increasingly being used to drive policies, to shape products and services, and for automated decision making.  It is therefore also important to understand the limitations around their use, especially when they are used to tackle significant societal challenges, such as humanitarian crises, climate change, minority issues, hate speech, and health -- social good applications that we will be overviewing in this talk.
I will end this talk with a brief viewpoint on research paths and impact.



Bio: Alexandra Olteanu is a computational social science and social computing researcher and a Data Science for Social Good Fellow at the IBM T.J. Watson Research Center. She is interested in how data and methodological limitations delimit what we can learn from online social traces. The problems she tackles are motivated by existing societal challenges such as hate speech, racial discrimination, climate change, and disaster relief. Her work has won two best paper awards (WISE 2014, Eurosys' SNS workshop 2012), and has been featured in the UN OCHA's “World Humanitarian Data and Trends” and in popular media outlets. More recently, she co-authored a survey of biases and methodological pitfalls when working with online social data, and has been co-organizing several tutorials on the topic at a variety of major data mining, and web and social media conferences, including ICWSM, KDD, WSDM, WWW, CHI, and SDM. She severs on the program committees of the main social media and web conferences, including ICWSM, WWW, WebSci, CIKM, and SIGIR.



2:30 - 2:40 Short Paper: Nada Mimouni and Timothy Yu-Cheong Yeung. Comparing Performance of Pre-processing Methods of Texts for Predicting a Binary Position by LASSO 


2:40 - 3:00 Full Paper: Dipasree Pal, Mandar Mitra, and Samar Bhattacharya. Query Expansion Using Term Distribution and Term Association


 
Break

Session 2 (3:40pm-5:00pm)

3:40 - 3:50 Invited Presentation 1: Maja Rudolph, Dynamic Embeddings for Language Evolution


3:50 - 4:00 Invited Presentation 2: Emma Pierson, Modeling Individual Cyclic Variation in Human Behavior 


4:00 - 4:10 Invited Presentation 3: Kaja Zupanc, Estimating Rule Quality for Knowledge Base Completion with the Relationship between Coverage Assumption 


4:10 - 4:20 Invited Presentation 4: Nina Grgic-Hlaca: Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction


4:20 - 4:30 Invited Presentation 5: Shweta Jain: A Fast and Provable Method for Estimating Clique Counts Using Turán’s Theorem


4:30 - 4:40 Invited Presentation 6: Huda Nassar: Multimodal Network Alignment

 

4:40 - 4:50 Invited Presentation 7: Ana-Andreea Stoica: Algorithmic Glass Ceiling in Social Networks: The effect of social recommender systems on diversity