scholars recommendation system
play

Scholars Recommendation System Based on academic knowledge graph - PowerPoint PPT Presentation

Scholars Recommendation System Based on academic knowledge graph Group member: Chengyongxiao Wei, Xianze Wu and Hanyi Sun CONTENTS n PART ONE Project Description n PART TWO Method n PART THREE Result n PART FOUR Conclusion CONTENTS n PART


  1. Scholars Recommendation System Based on academic knowledge graph Group member: Chengyongxiao Wei, Xianze Wu and Hanyi Sun

  2. CONTENTS n PART ONE Project Description n PART TWO Method n PART THREE Result n PART FOUR Conclusion

  3. CONTENTS n PART ONE Project Description n PART TWO Method n PART THREE Result n PART FOUR Conclusion

  4. Existing Work: Recommendation in Baidu

  5. Motivation Similar recommendation system is needed in academic field! • For students who want to find supervisors or scholars who have just entered a particular field. • Existing work: Co-authors recommendation in Google Scholar • Limitation: only utilizes co-author information •

  6. Motivation More significant information is in knowledge graph. • research fields, affiliations, conferences, etc. Based on those information, latent relationships • between scholars could be dug out. We aim at an real-time scholar recommendation • system based on AceKG, which recommends others according to the scholar being searched. ���������������������������������

  7. CONTENTS n PART ONE Project Description n PART TWO Method n PART THREE Result n PART FOUR Conclusion

  8. Methods ����������� ����������� ��� ��������� ��� ��������� ������ �� ��� ���� �..�������� ���������������������������� ��� ���� ����� �������� ��������������� ���������� �������� ����� ��� ��������� ��� ��������� ���� �� ������������ �������� .�� ����� ��� ���� ���� �� ���� ����� ��� ������� ������� ��� ������������������ �� ��� ���� .�����

  9. Recommendation based on cooperation network For a given scholar, recommend authors have close connection with him/her “Cross-author cooperation”: Direct cooperation: A and B don’t collaborate, but A and B are coauthors both of them cooperate with C. author A author A Paper 1 Paper 1 author C author B author B Paper 2

  10. Recommendation based on research fields For a given author, recommend important scholars on his/her research fields. • Significant scholars and their works benefit users to get familiar with this field. • Focus on scholars who are important in several fields or critical in a field. • Obtain significant scholars by important papers.

  11. Recommendation based on affiliation For a given author, recommend similar scholars in the same affiliation. Express similarity between scholars by the overlap • of research fields A variant of TF-IDF algorithm: • (&ℎ/42. & ∈ >: 43(6 /0 &2)53526-( 03-45 0 ∈ ": 6/1 10 03-45( /0 6ℎ- D3E-) 2*6ℎ/. !" #$ = & ' ( )*+,-. /0 121-.( 3) 03-45 0 & ' ( 6/624 )*+,-. /0 121-.( )*+,-. /0 (&ℎ/42.( 3) > 78" $ = log( )*+,-. /0 (&ℎ/42.( 3) > 2)5 "3-45 0)

  12. Recommendation based on conferences Recommend scholars who have published papers in same conference Utilize Author è Paper è Conference è Paper è Author information in academic knowledge graph paper paper paper conference paper author author … … … paper conference paper paper paper

  13. CONTENTS n PART ONE Project Description n PART TWO Method n PART THREE Result n PART FOUR Conclusion

  14. Case study: with direct cooperation with direct cooperation and “cross-author cooperation” without “cross-author cooperation”

  15. Demo Prof. Xinbing Wang: http://acemap.sjtu.edu.cn/authorTmp/page?AuthorID=7E0DFF97 Prof. Luoyi Fu: http://acemap.sjtu.edu.cn/authorTmp/page?AuthorID=80008266 Prof. Xiaohua Tian: http://acemap.sjtu.edu.cn/authorTmp/page?AuthorID=80A899B4

  16. CONTENTS n PART ONE Project Description n PART TWO Methods n PART THREE Result n PART FOUR Conclusion

  17. Conclusion In our project, we designed a real-time recommendation system based on academic knowledge graph, which • recommend scholars in three dimensions: cooperation network, research fields and affiliations. Besides, we finished offline recommendation based on conference. Task Division: • Chengxiaoyong Wei: • recommendation algorithm based on cooperation network, apply algorithms to Acemap Xianze Wu: • recommendation algorithm based on research fields and affiliation, apply algorithms to Acemap, UI design Hanyi Sun: • recommendation algorithm based on conference, UI design

  18. Thanks

Recommend


More recommend