Bichen Shi
 Ph.D Candidate
 University College Dublin,
 Dublin, Ireland

 Email: Bichen.Shi@insight-centre.org
 Office: G26, Science Centre(North), UCD Belfield

Research Interests:
  • Machine Learning & Data Mining in Real-time
  • Social Network Data Analysis

Education:
  • Doctor of Philosophy (Ph.D) in Computer Science & Informatics, University College Dublin, Dublin, Ireland (Sep 2013 - Present)
Supervisor: Dr. Neil Hurley and Dr.Georgiana Ifrim

  • Master's degree by research (M.Sc.) in Computer Science, University College Cork, Cork, Ireland (2013)
Thesis: A Machine Learning Approach to Estimating the Smoothed Complexity of Sorting Algorithms (pdf)

  • Bachelor's degree (B.Sc.) in Computer Science, University College Cork, Cork, Ireland (2012)
  • Bachelor's degree (B.Sc.) in Computer Science, Beijing Technology and Business University, Beijing, China (2012)

Papers:
  • Shi, Bichen.; Schellekens, Michel P.; Ifrim, Georgiana. 2014. A Machine Learning Approach to Estimating the Smoothed Complexity of Sorting Algorithms. arXiv:1503.06572, 2015 (pdf)
  • Shi, Bichen.; Ifrim, Georgiana; Hurley, Neil. Be In The Know: Connecting News Articles to Relevant Twitter Conversations. In Proceedings of the ECML/PKDD 2014 PhD Track.(pdf)
  • Shi, Bichen.; Ifrim, Georgiana; Hurley, Neil. Insight4News: Connecting News to Relevant Social ConversationsIn Proceedings of the ECML/PKDD 2014 Demo Track.(pdf)
  • Ifrim, Georgiana; Shi, Bichen.; Brigadir, Igor. Event Detection in Twitter using Aggressive Filtering and Hierarchical Tweet ClusteringIn Proceedings of the SNOW 2014 Data Challenge, WWW, 2014 (pdf)
  • Shi, Bichen.; Ifrim, Georgiana; Hurley, Neil. Be In The Know: Connecting News Articles to Relevant Twitter Conversations. arXiv:1405.3117, 2014.(pdf)
  • Schellekens, Michel P.; Hennessy, Aoife; Shi, Bichen. 2014. Modular smoothed analysis. [Preprint] (pdf)

Projects & Downloads:
Insight4News is a system that connects news articles to social conversations, in order to provide a richer context for ongoing and past news stories. The system extracts relevant topics that summarise the tweet activity around each article, recommends relevant hashtags, and presents complementary views and statistics on the tweet activity, related news articles, and timeline of the story with regards to Twitter reaction. 
Label Data for Hashtagger: here

Extract newsworthy topics from given Twitter stream every 15 minus.
Data collection & Python2 code(final version): here
Data collection & Python3 code: here  
Reference: pdf
                                                                                                                             
  • Twitter Hashtagger (2014)
Recommend relevant Twitter Hashtags for news articles. 
Python 3 code: here
Reference: pdf
                                                                                                                                                            
  • Machine Learning & Smoothed Complexity (Master project 2013)
Estimating the smoothed complexity of sorting algorithms using a machine learning approach(linear/non-linear regression & surface fitting)
Data collection & R code: here
Reference: pdf     
                                                                                                                                                                
  • Machine Learning with Tree Search for Connect-4 (B.Sc. final year project 2012) 
A connect-4 game agent using unsupervised learning(TD-predication) and tree search(Minmax)
Java code: here
Reference: pdf