From Social Graph to Interest Graph
In short: How online feeds moved from showing us the people we know to predicting what we may like, and how the explore-exploit dilemma shared by slime molds, birds and fish points to recommendation that widens curiosity.
A 2:07 short film in the series “Being Social Online”, narrated by intellect_voice_01.
Sources used in this film: Academia.edu (hosting a 2007 article from the Journal of Computer-Mediated Communication), “Social Network Sites: Definition History and Scholarship”; American Psychological Association (APA PsycNet), “Social network sites: Definition, history, and scholarship.”; Cornell University (Networks course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090), “The Shift From Social Graphs to Socio-interest Graphs within Social Media Algorithms : Networks Course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090”; Stanford University, CS 224W course (student final project by Aparna Krishnan and Raghav Ramesh, Group 41), “cs224w-041-final.pdf”; Tsinghua University researchers (Sukiennik, Li, Gao), published in the Proceedings of the ACM Web Conference 2024 (WWW '24), ACM, “Uncovering the Deep Filter Bubble: Narrow Exposure in Short-Video Recommendation”; Proceedings of the ACM Web Conference 2024 (WWW ’24), by Vombatkere, Mousavi, Zannettou, Roesner and Gummadi; hosted on a University of Washington faculty page, “TikTok and the Art of Personalization: Investigating Exploration and Exploitation on Social Media Feeds”; Google research paper (Covington, Adams, Sargin), presented at ACM RecSys 2016 and hosted on a UC San Diego course page, “p191-covington.pdf”; Google (Google Research; paper presented at ACM RecSys 2016), “45530.pdf”; Foundations and Trends in Human–Computer Interaction (survey by M. D. Ekstrand, J. T. Riedl and J. A. Konstan, University of Minnesota), hosted on a Northeastern University course page, “hci-009.dvi”; PNAS Nexus (Oxford University Press on behalf of the National Academy of Sciences), hosted on PubMed Central by the US National Library of Medicine, “Nudging recommendation algorithms increases news consumption and diversity on YouTube”; The Institute of Electronics, Information and Communication Engineers (IEICE), IEICE Transactions on Information and Systems, hosted on J-STAGE; paper by Jungkyu Han and Hayato Yamana, Waseda Univers…, “A Survey on Recommendation Methods Beyond Accuracy”; PubMed Central (PMC), U.S. National Library of Medicine; article published in Current Opinion in Behavioral Sciences, “Balancing exploration and exploitation with information and randomization”; Cornell University and Microsoft Research (paper in Proceedings of WSDM'18, Association for Computing Machinery), “Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration”.
Sources used in this film
- Academia.edu (hosting a 2007 article from the Journal of Computer-Mediated Communication) — Social Network Sites: Definition History and Scholarship · View →
- American Psychological Association (APA PsycNet) — Social network sites: Definition, history, and scholarship. · View →
- Cornell University (Networks course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090) — The Shift From Social Graphs to Socio-interest Graphs within Social Media Algorithms : Networks Course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090 · View →
- Stanford University, CS 224W course (student final project by Aparna Krishnan and Raghav Ramesh, Group 41) — cs224w-041-final.pdf · View →
- Tsinghua University researchers (Sukiennik, Li, Gao), published in the Proceedings of the ACM Web Conference 2024 (WWW '24), ACM — Uncovering the Deep Filter Bubble: Narrow Exposure in Short-Video Recommendation · View →
- Proceedings of the ACM Web Conference 2024 (WWW ’24), by Vombatkere, Mousavi, Zannettou, Roesner and Gummadi; hosted on a University of Washington faculty page — TikTok and the Art of Personalization: Investigating Exploration and Exploitation on Social Media Feeds · View →
- Google research paper (Covington, Adams, Sargin), presented at ACM RecSys 2016 and hosted on a UC San Diego course page — p191-covington.pdf · View →
- Google (Google Research; paper presented at ACM RecSys 2016) — 45530.pdf · View →
- Foundations and Trends in Human–Computer Interaction (survey by M. D. Ekstrand, J. T. Riedl and J. A. Konstan, University of Minnesota), hosted on a Northeastern University course page — hci-009.dvi · View →
- PNAS Nexus (Oxford University Press on behalf of the National Academy of Sciences), hosted on PubMed Central by the US National Library of Medicine — Nudging recommendation algorithms increases news consumption and diversity on YouTube · View →
- The Institute of Electronics, Information and Communication Engineers (IEICE), IEICE Transactions on Information and Systems, hosted on J-STAGE; paper by Jungkyu Han and Hayato Yamana, Waseda Univers… — A Survey on Recommendation Methods Beyond Accuracy · View →
- PubMed Central (PMC), U.S. National Library of Medicine; article published in Current Opinion in Behavioral Sciences — Balancing exploration and exploitation with information and randomization · View →
- Cornell University and Microsoft Research (paper in Proceedings of WSDM'18, Association for Computing Machinery) — Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration · View →
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Academia.edu (hosting the 2007 Journal of Computer-Mediated Communication article 'Social Network Sites: Definition, His: Social Network Sites: Definition History and Scholarship
- Also: American Psychological Association (APA PsycNet): Social network sites: Definition, history, and scholarship.
- Also: Cornell University (Networks course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090): The Shift From Social Graphs to Socio-interest Graphs within Social Media Algorithms : Networks Course blog for INFO 2040/CS 2850/Econ 2040/SOC 2090
- Also: Stanford University, CS 224W course (student final project by Aparna Krishnan and Raghav Ramesh, Group 41): cs224w-041-final.pdf
- Also: Tsinghua University researchers (Sukiennik, Li, Gao), published in the Proceedings of the ACM Web Conference 2024 (WWW ': Uncovering the Deep Filter Bubble: Narrow Exposure in Short-Video Recommendation
- Also: Proceedings of the ACM Web Conference 2024 (WWW ’24), by Vombatkere, Mousavi, Zannettou, Roesner and Gummadi; hosted on : TikTok and the Art of Personalization: Investigating Exploration and Exploitation on Social Media Feeds
- Also: Google research paper (Covington, Adams, Sargin), presented at ACM RecSys 2016 and hosted on a UC San Diego course page: p191-covington.pdf
- Also: Google (Google Research; paper presented at ACM RecSys 2016): 45530.pdf
- Also: Foundations and Trends in Human–Computer Interaction (survey by M. D. Ekstrand, J. T. Riedl and J. A. Konstan, Universit: hci-009.dvi
- Also: PNAS Nexus (Oxford University Press on behalf of the National Academy of Sciences), hosted on PubMed Central by the US N: Nudging recommendation algorithms increases news consumption and diversity on YouTube
- Also: The Institute of Electronics, Information and Communication Engineers (IEICE), IEICE Transactions on Information and Sys: A Survey on Recommendation Methods Beyond Accuracy
- Also: PubMed Central (PMC), U.S. National Library of Medicine; article published in Current Opinion in Behavioral Sciences: Balancing exploration and exploitation with information and randomization
- Also: Cornell University and Microsoft Research (paper in Proceedings of WSDM'18, Association for Computing Machinery): Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration
To cite this card, link to https://intellectplus.co.uk/app/from-social-graph-to-interest-graph.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
