Mapping Academic Patents to Papers

1. Mapping Academic Patents to Papers Hyun-Woo Kim,1 Zhen Lei,1 Brian Wright,2 John Yen1 1 Penn State University 2 UC Berkeley NAS SciSIP PI Conference September 20-21, 2012

2. NSF SciSIP Project • Collaborative Research: • The Impacts of University Research and Funding Sources in Chemical Sciences: Publishing, Patenting, Commercialization • PIs: Brian Wright (UC Berkeley) and Zhen Lei (Penn State) • Role of research sponsor type (government or industry) on university research, patenting, technology transfer • Publishing, patenting, licensing/ MTAs, and diffusion and follow-on research of university inventions • Interplay between government and industry funding in university research

3. Datasets • Data 1: • Access to University of California Office of Technology Transfer: • Invention disclosures, patenting and licensing history • Sponsor information, technology information • Data 2: • All scientific publications in chemical sciences by UC researchers in 1975-2005, and the associated citation profile of these publications

4. Mapping Patents to Papers

5. Patent/Paper Correspondence:One-to-One in Theory A paper Same researchers Close dates An invention A patent

6. Not So Clean in Practice Patent filing Patent filing Continuation Grant Papers Papers

7. Features of a Patent-Paper Pair • Feature Group 1 (paper coauthors’ names): • Does first co-inventor’s last name appear in the co-author list? • Does first co-inventor’s “fist initial and last name” appear in the co-author list? • Does first co-author’s last name appear in the co-inventor list? • Does first co-author’s “fist initial and last name” appear in the co-inventor list? • Does last co-author’s last name appear in the co-inventor list? • Does last co-author’s “fist initial and last name” appear in the co-inventor list? • Fraction of patent inventors whose first initial and last name appear in the coauthor list of the paper • Fraction of patent inventors whose last names appear in the coauthor list of the paper

8. Features of a Patent-Paper Pair • Feature Group 2 (paper primary affiliation): • String similarity score (Levenshtein Distance) between patent assignee and paper primary affiliation • Percentage of the common words between patent assignee and paper primary affiliation • Is the patent assignees’ country the same as the paper primary affiliation’s? • Is the patent assignee’s (city or state)+country is the same is the paper primary affiliation’s? • Does first co-inventor’s country appear in the paper primary affiliation? • Does first co-inventor’s city/state and country appear in the paper primary affiliation? • Fraction of the inventors whose countries are same as the paper primary affiliation’s • Fraction of the inventors whose city/state and country are same as the paper primary affiliation’s

9. Features of a Patent-Paper Pair • Feature Group 3 (content similarity): • Fraction of the common words in patent and paper titles • Fraction of the common words in patent and paper abstracts • Fraction of the paper’s chemical substances that appear in patent title • Fraction of the paper’s chemical substances that appear in patent abstract

10. Features of a Patent-Paper Pair • Feature Group 4 (Timing): • Abs (Paper publication year – Patent filing year) • Abs (Paper publication year – Earliest patent filing year)

11. Data • Murray/Stern Data • 165 pairs of Nature Biotech paper /US patent • Our Experiment • 165 patents: 162 with one GT (ground truth) paper, 3 with 2 GTs • Retrieve papers from PubMed that share at least one last name • Filtering: • Exclude Review Articles • (Earliest patent filing year -2) TO (Patent filing year +5) • A total of 247322 patent-article pairs • 1498.92 articles/patent on average

12. Experiment 1 • 10-fold Cross Validation • Algorithms to Build Models Logistic Regression Normal-Identity Regression Binomial-LogLog Regression Binomial-Probit Regression An ensemble method averaging all above

13. Model Comparison (rank of GT) • Use all features Model Logistic Nor-Identity Bin-LogLog Bin-Probit Ensemble Upper Lower 3.1647 3.5393 3.5276 3.5276 3.0640 3.4449 3.1018 3.4765 2.8788 2.8788

14. Tagging • Evaluate top ranked papers for each patent to see if they are GTs as well? • 1120 patent-paper pairs have been evaluated and tagged. • Not GTs: 566 pairs • Uncertain: 4 pairs • GTs: 550 pairs

15. Histograms: (# of GTs per Patent) Before Tagging After Tagging

16. Experiment 2 • Updated GT papers for each patent • 10-fold Cross Validation • Algorithms to Build Models Logistic Regression Normal-Identity Regression Binomial-LogLog Regression Binomial-Probit Regression An ensemble method averaging all above

17. Model Comparison(rank of 1st GT) • Use all features Model Logistic Nor-Identity Bin-LogLog Bin-Probit Ensemble Upper Lower 1.0739 1.0739 1.1923 1.1923 1.0680 1.0680 1.0739 1.0739 1.0870 1.0870

18. Model Comparison (fraction of GTs in Top k) • Use all features

19. Summary • An algorithm to link patents to papers • Useful tool for studying dynamics and interaction in utilization of university inventions by both academia and industry, and impacts of university patenting and licensing • Useful tool for evaluating impacts of government funding

20. Thank you!zlei@psu.edu

21. Fraction of patent inventors whose last names appear in GT papers