Presentation at the IntRS at RecSys 2020. In collaboration with Chun-Hua Tsai, Thomas Olsson & Peter Brusilovsky.

1. Diversity Exposure in Social
Recommender Systems:
A Social Capital Theory
Perspective
Chun-Hua Tsai, Jukka Huhtamäki (@jnkka),
Thomas Olsson & Peter Brusilovsky
IntRS 2020 at RecSys2020
http://ceur-ws.org/Vol-2682/paper6.pdf

2. How to recommend people in conferences?
•Existing social structure, or the lack of one, tends to
direct the emergence of new ties in conferences
•For junior scholars and other newcomers, the
identification of relevant individuals or cliques is
laborious and characterized by chance
•For seniors, a key issue, perhaps counter-intuitively, is
the existence of their strong connecting tissue to the
core of the community that limits their networking
capability
26.9.2020 | 2

3. Key concepts
•Social capital: bonding and
bridging
(Putnam 2000, Granovetter 1973)
•Strong and weak ties
(Granovetter, 1973)
•Social diversity exposure
(see Helberger, Karppinen & D’Acunto, 2018)
26.9.2020 | 3
Image: Olsson, Huhtamäki & Kärkkäinen (2020)

4. Social capital in knowledge work
26.9.2020 | 4
• Social capital is a key driver of organizational
advantage: “the sum of the actual and potential
resources embedded within, available through,
and derived from the network of relationships
possessed by an individual or social unit”
(Nahapiet & Ghoshal, 1998)
• Two types of social capital, bridging and
bonding. Bonding consists of strong ties,
bridging capital of weak ties (Putnam 2000,
Granovetter 1973)
• Brokerage in a social network is a favorable
position to an actor (Burt, 2004)

5. Social capital accumulation
• Social capital is dynamic: “The existence of a network of
connections is not a natural given, or even a social given,
constituted once and for all by an initial act of institution [...] It is
the product of an endless effort at institution.” (Bourdieu, 1986)
• Network evolution is prone to biases: homophily (Kossinets & Watts,
2009), triadic closure (Granovetter, 1973), and in some cases
preferential attachment (Barabási & Albert, 1999)
• Social capital accumulates one network connection at a time.
Here, we explore how to support the selection of these
connections with a people recommender system
26.9.2020 | 5

6. Relevance-first vs. diversity exposure
•Key mechanisms driving the evolution of a social
network are homophily and triadic closure
•A relevance-first approach to recommend new people is
likely to amplify these mechanism, leading into tightly
connected social communities
•Instead, to counter-balance the natural evolution of
social networks, we suggest to focus on social diversity
exposure and the identification of weak ties for bridging
social capital
26.9.2020 | 6

7. Illustrative
case study
26.9.2020 | 7

8. First insights
26.9.2020 | 8
• 170 participants at EC-TEL 2017
• Conference Navigator (CN3) (Tsai &
Brusilovsky, 2016)

9. Reflections
• Capturing real-life social works: the proceedings publication
certainly gives a very limited view
• Alternative to social diversity exposure: transparency of
algorithms and interfaces
• Yet, people are prone to homophily and triadic closure
• Are we able to able to algorithmically argue for the importance
of social diversity exposure and the accumulation of bridging
social capital?
• The ethics of nudging: technology is never neutral
• Finally, do we need (social) theory in RecSys research?
26.9.2020 | 9

10. Additional reading
• Digital Social Matching in Professional Life: Lessons from the Big Match project
• Huhtamäki, J., Olsson, T., & Laaksonen, S.-M. (2020). Facilitating Organisational Fluidity with
Computational Social Matching. In H. Lehtimäki, P. Uusikylä, & A. Smedlund (Eds.), Society as an
Interaction Space: A Systemic Approach (pp. 229–245). Springer.
• Olshannikova, E., Olsson, T., Huhtamäki, J., & Yao, P. (2019). Scholars’ Perceptions of Relevance in
Bibliography-based People Recommender System. Computer Supported Cooperative Work
(CSCW), 28(3–4), 357–389.
• Olshannikova, E., Olsson, T., Huhtamäki, J., Paasovaara, S., & Kärkkäinen, H. (2020). From
Chance to Serendipity: Knowledge Workers’ Experiences of Serendipitous Social Encounters.
Advances in Human-Computer Interaction, 2020, 18.
• Olsson, T., Huhtamäki, J., & Kärkkäinen, H. (2020). Directions for Professional Social Matching
Systems. Communications of the ACM, 63(2), 60–69.
• Skenderi, E., Olshannikova, E., Olsson, T., Huhtamäki, J., Koivunen, S., Yao, P., & Huttunen, H.
(2019). Investigation of Egocentric Social Structures for Diversity-Enhancing Followee
Recommendations. Adjunct Publication of the 27th Conference on User Modeling, Adaptation and
Personalization - UMAP’19 Adjunct, 257–261.
26.9.2020 | 10@jnkka