ColdRoute: effective routing of cold questions in stack exchange sites
- The Ohio State Univ., Columbus, OH (United States)
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Microsoft, Albuquerque, NM (United States)
Routing questions in Community Question Answer services such as Stack Exchange sites is a well-studied problem. Yet, cold-start—a phenomena observed when a new question is posted is not well addressed by existing approaches. Additionally, cold questions posted by new askers present significant challenges to state-of-the-art approaches. We propose ColdRoute to address these challenges. ColdRoute is able to handle the task of routing cold questions posted by new or existing askers to matching experts. Specifically, we use Factorization Machines on the one-hot encoding of critical features such as question tags and compare our approach to well-studied techniques such as CQARank and semantic matching (LDA, BoW, and Doc2Vec). Furthermore by using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision@1, Accuracy, MRR) over the state-of-the-art models such as semantic matching by 159.5, 31.84, and 40.36% for cold questions posted by existing askers, and 123.1, 27.03, and 34.81% for cold questions posted by new askers respectively.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1460547
- Journal Information:
- Data Mining and Knowledge Discovery, Journal Name: Data Mining and Knowledge Discovery Journal Issue: 5 Vol. 32; ISSN 1384-5810
- Country of Publication:
- United States
- Language:
- English
Modeling problem difficulty and expertise in stackoverflow
|
conference | January 2012 |
Ranking user authority with relevant knowledge categories for expert finding
|
journal | April 2013 |
Exploring user expertise and descriptive ability in community question answering
|
conference | August 2014 |
Predicting Best Answerers for New Questions: An Approach Leveraging Distributed Representations of Words in Community Question Answering
|
conference | August 2015 |
Factorization Machines
|
conference | December 2010 |
Scalable Coordinate Descent Approaches to Parallel Matrix Factorization for Recommender Systems
|
conference | December 2012 |
Hierarchies in Directed Networks
|
conference | November 2015 |
Expert Finding for Question Answering via Graph Regularized Matrix Completion
|
journal | April 2015 |
Social Recommendation with Cross-Domain Transferable Knowledge
|
journal | November 2015 |
Topic-Level Expert Modeling in Community Question Answering
|
conference | December 2013 |
Expertise networks in online communities: structure and algorithms
|
conference | January 2007 |
Identifying authoritative actors in question-answering forums: the case of Yahoo! answers
|
conference | January 2008 |
Tapping on the potential of q&a community by recommending answer providers
|
conference | January 2008 |
The anatomy of a large-scale social search engine
|
conference | January 2010 |
Routing questions to appropriate answerers in community question answering services
|
conference | January 2010 |
Competition-based user expertise score estimation
|
conference | January 2011 |
I want to answer; who has a question?
|
conference | August 2011 |
Question routing in community question answering: putting category in its place
|
conference | January 2011 |
Towards expert finding by leveraging relevant categories in authority ranking
|
conference | January 2011 |
Modeling problem difficulty and expertise in stackoverflow
|
conference | January 2012 |
Factorization Machines with libFM
|
journal | May 2012 |
A classification-based approach to question routing in community question answering
|
conference | January 2012 |
Discovering value from community activity on focused question answering sites: a case study of stack overflow
|
conference | January 2012 |
Dual role model for question recommendation in community question answering
|
conference | January 2012 |
Adapting vector space model to ranking-based collaborative filtering
|
conference | January 2012 |
Topic-sensitive probabilistic model for expert finding in question answer communities
|
conference | January 2012 |
Learning to rank for hybrid recommendation
|
conference | January 2012 |
Question-answer topic model for question retrieval in community question answering
|
conference | January 2012 |
Competition-based networks for expert finding
|
conference | January 2013 |
Ad click prediction: a view from the trenches
|
conference | January 2013 |
When relevance is not enough: promoting diversity and freshness in personalized question recommendation
|
conference | January 2013 |
CQArank: jointly model topics and expertise in community question answering
|
conference | January 2013 |
SocialTransfer: Transferring Social Knowledge for Cold-Start Cowdsourcing
|
conference | January 2014 |
Mining Shapes of Expertise in Online Social Q&A Communities
|
conference | January 2016 |
A Comprehensive Survey and Classification of Approaches for Community Question Answering
|
journal | August 2016 |
node2vec: Scalable Feature Learning for Networks
|
conference | January 2016 |
Summarizing Answers in Non-Factoid Community Question-Answering
|
conference | January 2017 |
Learning to Recommend Accurate and Diverse Items
|
conference | January 2017 |
Breaking Cycles In Noisy Hierarchies
|
conference | January 2017 |
A Data-Driven Approach to Question Subjectivity Identification in Community Question Answering
|
journal | September 2021 |
Learning to Rank Effective Paraphrases from Query Logs for Community Question Answering
|
journal | June 2013 |
Question/Answer Matching for CQA System via Combining Lexical and Sequential Information
|
journal | February 2015 |
Learning Entity and Relation Embeddings for Knowledge Graph Completion
|
journal | February 2015 |
Community-Based Question Answering via Heterogeneous Social Network Learning
|
journal | February 2016 |
Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning
|
journal | February 2017 |
Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora
|
conference | January 2009 |
A Regularized Competition Model for Question Difficulty Estimation in Community Question Answering Services
|
conference | January 2014 |
Similar Records
An approach for collaborative development of a federated biomedical knowledge graph-based question-answering system: Question-of-the-Month challenges
Routing of ultrahazardous materials - More questions than answers