S2DS final project presentation: Building a recommendation engine for RefME
2 likes804 views
RefMe, an award-winning referencing tool, aims to enhance its product by developing a bibliography recommendation engine to assist users, particularly undergraduates, in generating relevant references for their academic work. The engine utilizes a combination of collaborative filtering and content-based recommendations, drawing from a database of 21,000 projects with over 120,000 user-generated references. This feature is planned to be offered as a premium addition to the existing platform.
S2DS final project presentation: Building a recommendation engine for RefME
- 1. Building a Library Recommendation Engine www.refme.com @getrefme Martina Pugliese Daniel Pape Richard Hanson
- 2. What is RefME? • award-winning referencing tool! • synchronised website + mobile app! • easy to use! • barcode scanning! • many reference types! • import from several formats! • export in 1000s of styles 2 / 13
- 3. Who uses RefME? • 100 000s users! • mainly undergraduate students! • writing essays, theses, building bibliographies! • Other tools focus on academic market! • RefME is much more general 3 / 13
- 4. Our Task 4 RefME wants to broaden the appeal of their product by offering a tool to build better bibliographies. / 13
- 5. Our Task 4 RefME wants to broaden the appeal of their product by offering a tool to build better bibliographies. / 13 “take the search out of research”
- 6. Our Task Task: Develop a recommendation system! • suggest relevant references to users! • general enough to handle any reference type 4 RefME wants to broaden the appeal of their product by offering a tool to build better bibliographies. / 13 “take the search out of research”
- 7. The Data • small subset of data-base! • 21 000 projects with 120 000+ references! • references are user-generated and associated via projects! • pre-processing: sort/unify identifiers (isbn, doi, url) + retrieve subject keywords Recommendation! Engine Project ID Reference IDs 5 / 13
- 8. Collaborative Filtering Content-based Recommendations 6 / 13 Our Recommendation Engine “ask your friends” “look at content information”
- 9. Collaborative Filtering Project Based similar projects nearest neighbours 7 / 13
- 10. Project Based Reference Based similar projects nearest neighbours interaction patterns co-occurrence Collaborative Filtering 7 / 13
- 11. Collaborative Filtering Project Based Reference Based similar projects nearest neighbours interaction patterns co-occurrence multiple similarity measures for robust results 7 / 13
- 12. Collaborative Filtering Project Based Reference Based similar projects nearest neighbours interaction patterns co-occurrence multiple similarity measures for robust results recommendations 7 / 13
- 13. Collaborative Filtering Content-based Recommendations 8 / 13
- 14. Content-based Recommendations 9 / 13
- 15. Content-based Recommendations no references 9 / 13
- 16. Content-based Recommendations no references project title compare titles with NLP retrieve subjects in matching projects extract references based on subject frequency 9 / 13
- 17. Content-based Recommendations no references with references project title compare titles with NLP retrieve subjects in matching projects extract references based on subject frequency 9 / 13
- 18. Content-based Recommendations no references with references project title subject keywords compare titles with NLP retrieve subjects in matching projects extract references based on subject frequency measure similarity extract most similar references 9 / 13
- 19. Benefits of two approaches Collaborative Filtering Content-based Recommendations 10 / 13 independent of item frequency good for common topics good for items with sufficient frequency
- 20. Project: “Media Research” • Relocating Television: Television in the Digital Context • Transmedia Television: Audiences, New Media and Daily Life • Television and Its Audience • Television Goes Digital. The Economics of Information Communication and Entertainment: The Impacts of Digital Technology in the 21st Century. OUTPUT INPUT 11 / 13 • Grown Up Digital How the Net Generation is Changing Your World • Future Minds: How the Digital Age is Changing Our Minds Why This Matters and What We Can Do About It • The Television Studies Book • Television and Everyday Life
- 21. Project: “Group Presentation” • Person to Person: Ways of Communicating • The Psychology of Interpersonal Perception • Interpersonal Communication • Body Movement and Interpersonal Communication • Intergroup Behaviour OUTPUT INPUT 12 / 13 • The Social Psychology of Everyday • Interviews Made Easy How to Get the Psychological Advantage • Groups at Work: Theory and Research • Theories of Human Communication (with InfoTrac)
- 22. 13 Summary / 13 RefME wants to broaden the appeal of their product by offering a tool to build better bibliographies. Developed recommendation system! • yields good results for any reference type! • will be incorporated as premium feature soon
- 23. www.refme.com @getrefme Martina Pugliese Daniel Pape Richard Hanson
- 24. Used Tools • Python NLTK libraries! • openlibrary.org API! • crossref.org API! • mahout.apache.org! • R, Java