Diyi Yang

Ph.D Student, LTI@CMU

I work on using natural language processing techniques to solve problems in computational social science, with the implication of developing new algorithms to enhance online interaction.

I am very lucky to be co-advised by Robert E. Kraut and Eduard Hovy.

  • Phone+1 (412) 980 8543
  • Emaildiyiy@cs.cmu.edu
  • OfficeGHC 5507

NEWS

  • 2016.05 - We got Best Paper Honorable Mention at ICWSM 2016!
  • 2016.05 - I got CMU Presidential Fellowship!
  • 2016.05 - Intern at Microsoft Research Redmond :-)

Education
  • NameDiyi Yang
  • Phone+1 (412) 980 8543
  • Emaildiyiy@cs.cmu.edu
  • Status3rd-year Ph.D. Student
Download My Resume

EDUCATION

Ph.D in Language Technologies2015 - Present

Carnegie Mellon University

Advised by Robert E. Kraut and Eduard Hovy.

M.S in Language Technologies2013 - 2015

Carnegie Mellon University

Advised by Carolyn P. Rose.

Bachelor of Engineering2009 - 2013

Shanghai Jiaotong University

ACM Honored Class, advised by Yong Yu.

AWARDS & HONORS

Best Paper Honorable Mention, ICWSM2016

Presidential Fellowship, CMU2016-2017

CMU GSA Conference Funding2016

EMNLP 2015 Notable Data Set Award2015

Learning at Scale Student Travel Grant, ACM2015

Excellent Undergraduate, SJTU2013

5th Place in KDD Cup 2013, Track 22013

Google Anita Borg Scholarship2012

SIGIR Student Travel Grant2012

Champion in KDD Cup 2012, Track 12012

Best Paper Award Candidate, International Conference on Web intelligence2012

Publications
  1. Who does What: Editor Role Identification in Wikipedia
    Diyi Yang, Aaron Halfaker, Robert Kraut and Eduard Hovy
    ICWSM, 2016. Best Paper Honorable Mention. [pdf]
    In the news: [CMU LTI], [Wikimedia Newsletter]
  2. Hierarchical Attention Networks for Document Classification
    Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola and Eduard Hovy
    NAACL, 2016. [pdf]
  3. Edit Categories and Editor Role Identification in Wikipedia
    Diyi Yang, Aaron Halfaker, Robert Kraut and Eduard Hovy
    LREC, 2016. [pdf] [data]
  4. Humor Recognition and Humor Anchor Extraction
    Diyi Yang, Alon Lavie, Chris Dyer and Eduard Hovy
    EMNLP 2015, oral. [pdf]
  5. Weakly Supervised Role Identification in Teamwork Interactions
    Diyi Yang, Miaomiao Wen, Carolyn Rose
    ACL 2015, oral. [pdf]
  6. That's So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets
    William Yang Wang, Diyi Yang
    EMNLP 2015, Notable Data Set Award: 2/1300, 0.2%. [pdf] [data]
  7. Exploring the Effect of Confusion in Discussion Forums of Massive Open Online Courses
    Diyi Yang, Miaomiao Wen, Iris Howley, Robert Kraut, Carolyn Rose
    Learning at Scale, 2015. [pdf]
  8. Incorporating Word Correlation Knowledge into Topic Modeling
    Pengtao Xie, Diyi Yang, Eric Xing
    NAACL, 2015. [pdf]
  9. How does students cognitive behavior in MOOC discussion forums affect their learning gains?
    Xu Wang, Diyi Yang, Miaomiao Wen, Kenneth Koedinger, Carolyn Rose
    Proc. 8th Intl. Conf. on Educational Data Mining, 2015. [pdf]
  10. Positive Impact of Collaborative Chat Participation in an edX MOOC
    Oliver Ferschke, Diyi Yang, Gaurav Tomar, Carolyn Rose
    AIED, 2015. [pdf]
  11. Question Recommendation with Constraints for Massive Open Online Courses
    Diyi Yang, David Adamson, Carolyn Rose
    RecSys 2014. [pdf]
  12. Constrained Question Recommendation in MOOCs via Submodularity
    Diyi Yang, Jingbo Shang, Carolyn Rose
    CIKM 2014. [pdf]
  13. Forum Thread Recommendation for Massive Open Online Courses
    Diyi Yang, Mario Piergallini, Iris Howley, Carolyn Rose
    Proc. 7th Intl. Conf. on Educational Data Mining, 2014. [pdf]
  14. Peer Influence on Attrition in Massive Open Online Courses
    Diyi Yang, Miaomiao Wen, Carolyn Rose
    Proc. 7th Intl. Conf. on Educational Data Mining, 2014. [pdf]
  15. Sentiment Analysis in MOOC Discussion Forums: What does it tell us?
    Miaomiao Wen, Diyi Yang, Carolyn Rose
    Proc. 7th Intl. Conf. on Educational Data Mining, 2014. [pdf]
  16. Linguistic Reflections of Student Engagement in Massive Open Online Courses
    Miaomiao Wen, Diyi Yang, Carolyn Rose
    ICWSM, 2014. [pdf]
  17. Social Factors that Contribute to Attrition in MOOCs
    Carolyn Rose, Ryan Carlson, Diyi Yang, Miaomiao Wen, Lauren Resnick, Pam Goldman, Jennifer Sheerer
    Learning at Scale, 2014. [pdf]
  18. Predicting Advertiser Bidding Behaviors in Sponsored Search by Rationality Modeling
    Haifeng Xu, Bin Gao, Diyi Yang, Tie-Yan Liu
    WWW, 2013. [pdf]
  19. Collaborative Filtering with Short Term Preferences Mining
    Diyi Yang, Tianqi Chen, Weinan Zhang, Yong Yu
    SIGIR 2012. [pdf]
  20. Local Implicit Feedback Mining for Music Recommendation
    Diyi Yang, Tianqi Chen, Weinan Zhang, Qiuxia Lu, Yong Yu
    RecSys 2012. [pdf]
  21. Serendipitous Personalized Ranking for Top-N Recommendation
    Qiuxia Lu, Tianqi Chen, Weinan Zhang, Diyi Yang, Yong Yu
    WI 2012, Best Paper Award Candidate. [pdf]
  1. Exploring the Effect of Student Confusion in Massive Open Online Courses
    Diyi Yang, Robert Kraut and Carolyn Rose
    Journal of Educational Data Mining (JEDM), Under Review.
  2. Towards an Integration of Text and Graph Clustering Methods as a Lens for Studying Social Interaction in MOOCs
    Diyi Yang, Miaomiao Wen, Abhimanu Kumar, Eric Xing, Carolyn Rose
    International Review of Research in Open and Distance Learning, Special Issue on the MOOC Research Initiative. [pdf]
  1. A Lightly Supervised Approach to Role Identification in Wikipedia Talk Page Discussions
    Oliver Ferschke, Diyi Yang, Carolyn P. Rose
    ICWSM 2015 Workshop on Wikipedia. [pdf]
  2. Towards Identifying the Resolvability of Threads in MOOCs
    Diyi Yang, Miaomiao Wen, Carolyn Rose
    EMNLP 2014 on MOOC Workshop. [pdf]
  3. Turn on, Tune in, Drop out: Anticipating student dropouts in Massive Open Online Courses
    Diyi Yang, Tanmay Sinha, David Adamson, Carolyn Rose
    NIPS 2013 on Data Driven Education Workshop. [pdf]
  4. Combining Factorization Model and Additive Forest for Collaborative Followee Recommendation
    Tianqi Chen, Linpeng Tang, Qin Liu, Diyi Yang, Saining Xie, Xuezhi Cao, Chunyang Wu, Enpeng Yao, Zhengyang Liu, Zhansheng Jiang, Cheng Chen, Weihao Kong, Yong Yu
    KDD Cup 2012, Champion. [pdf]
Experience

INTERNSHIPS

Research InternMay 2016 - Aug 2016

Microsoft Research Redmond

Social Computing Group, advised by Scott Counts.

Research InternJune 2015 - Sep 2015

Wikimedia Foundation

Role Identification in Wikipedia, advised by Aaron Halfaker.

Research InternJuly 2012 - Feb 2013

Microsoft Research Asia

Artificial Intelligence Group, advised by Bin Gao.

SERVICES

Reviewer2016

NAACL, EMNLP, LREC

TALKS & PRESENTATIONS

Humor Recognition and Humor Anchor Extraction

The 2015 Conference on Empirical Methods on Natural Language Processing, Lisbon, Portugal, 2015.

Weakly Supervised Role Identification in Teamwork Interactions

The 53rd Annual Meeting of the Association for Computational Linguistics, Beijing, China, 2015.

Exploring the Effect of Confusion in Discussion Forums of Massive Open Online Courses

The 2nd Annual ACM Conference on Learning at Scale, Vancouver, BC, Canada, 2015.

Question Recommendation with Constraints for Massive Open Online Courses

The 8th ACM Recommender Systems, Foster City, USA, 2014.

Social and Motivational Factors Associated with Attrition in MOOCs

Poster presentation, Global Learning Council, September 2014.

Question Recommendation with Constraints for Massive Open Online Courses

Student Research Symposium, Carnegie Mellon University, July, 2014.

Forum Thread Recommendation for Massive Open Online Courses

The 7th International Conference on Educational Data Mining, London, UK, 2014.