Towards novelty-driven recommender systems

Pietro Gravino; Bernardo Monechi; Vittorio Loreto

doi:10.1016/j.crhy.2019.05.014

From statistical physics to social sciences/De la physique statistique aux sciences sociales

Towards novelty-driven recommender systems
[Vers des systèmes de recommandation axés sur la nouveauté]

Pietro Gravino ¹ ; Bernardo Monechi ¹ ; Vittorio Loreto ^1,^2,³

¹ Sony Computer Science Laboratories, Paris, 6, rue Amyot, 75005 Paris, France
² Sapienza University of Rome, Physics Department, Piazzale Aldo Moro 2, 00185 Roma, Italy
³ Complexity Science Hub, Josefstädter Strasse 39, A-1080 Wien, Austria

Comptes Rendus. Physique, Volume 20 (2019) no. 4, pp. 371-379.

Résumé
Abstract

Nous recevons des recommandations à propos de tout et d'une manière omniprésente. Les systèmes de recommandation agissent comme des boussoles pour notre voyage dans des espaces conceptuels complexes, et nous comptons de plus en plus sur les recommandations pour fonder la plupart de nos décisions. Malgré leur efficacité et leur fiabilité extraordinaires, les systèmes de recommandation sont loin d'être parfaits. Ils présentent plutôt de sérieux inconvénients qui pourraient sérieusement réduire notre ouverture d'esprit et notre capacité à faire l'expérience de la diversité et à avoir des opinions contradictoires. Dans cet article, nous examinons attentivement les fondements mêmes des algorithmes de recommandation afin d'identifier les déterminants de ce que pourrait être la prochaine génération de systèmes de recommandation. Nous postulons qu'il est possible de surmonter les limites des systèmes de recommandation actuels en s'inspirant de la façon dont les gens recherchent les nouveautés et valorisent les nouvelles expériences. De ce point de vue, la notion de possible adjacent semble pertinente pour repenser les systèmes de recommandation d'une manière qui s'aligne mieux avec l'inclination naturelle des êtres humains vers des expériences nouvelles et agréables. Nous affirmons que cette nouvelle génération de prescripteurs pourrait aider à surmonter les écueils des technologies actuelles, à savoir la tendance au manque de diversité, à la polarisation, à l'émergence d'écho-chambres et à la désinformation.

We get recommendations about everything and in a pervasive way. Recommender systems act like compasses for our journey in complex conceptual spaces and we more and more rely on recommendations to ground most of our decisions. Despite their extraordinary efficiency and reliability, recommender systems are far from being flawless. They display instead serious drawbacks that might seriously reduce our open-mindedness and our capacity of experiencing diversity and possibly conflicting views. In this paper, we carefully investigate the very foundations of recommendation algorithms in order to identify the determinants of what could be the next generation of recommender systems. We postulate that it is possible to overcome the limitations of current recommender systems, by getting inspiration from the way in which people seek for novelties and give value to new experiences. From this perspective, the notion of adjacent possible seems a relevant one to redesign recommender systems in a way that better aligns with the natural inclination of human beings towards new and pleasant experiences. We claim that this new generation of recommenders could help in overcoming the pitfalls of current technologies, namely the tendency towards a lack of diversity, polarization, the emergence of echo-chambers and misinformation.

Publié le : 2019-05-01

DOI : 10.1016/j.crhy.2019.05.014

Keywords: Recommender systems, Novelties, Adjacent possible, Comfort zone
Mots-clés : Systèmes de recommandation, Nouveautés, Adjacente possible, Zone de confort

Affiliations des auteurs :

Pietro Gravino ¹ ; Bernardo Monechi ¹ ; Vittorio Loreto ^{1, 2, 3}

¹ Sony Computer Science Laboratories, Paris, 6, rue Amyot, 75005 Paris, France
² Sapienza University of Rome, Physics Department, Piazzale Aldo Moro 2, 00185 Roma, Italy
³ Complexity Science Hub, Josefstädter Strasse 39, A-1080 Wien, Austria

@article{CRPHYS_2019__20_4_371_0,
     author = {Pietro Gravino and Bernardo Monechi and Vittorio Loreto},
     title = {Towards novelty-driven recommender systems},
     journal = {Comptes Rendus. Physique},
     pages = {371--379},
     publisher = {Elsevier},
     volume = {20},
     number = {4},
     year = {2019},
     doi = {10.1016/j.crhy.2019.05.014},
     language = {en},
}

TY  - JOUR
AU  - Pietro Gravino
AU  - Bernardo Monechi
AU  - Vittorio Loreto
TI  - Towards novelty-driven recommender systems
JO  - Comptes Rendus. Physique
PY  - 2019
SP  - 371
EP  - 379
VL  - 20
IS  - 4
PB  - Elsevier
DO  - 10.1016/j.crhy.2019.05.014
LA  - en
ID  - CRPHYS_2019__20_4_371_0
ER  -

%0 Journal Article
%A Pietro Gravino
%A Bernardo Monechi
%A Vittorio Loreto
%T Towards novelty-driven recommender systems
%J Comptes Rendus. Physique
%D 2019
%P 371-379
%V 20
%N 4
%I Elsevier
%R 10.1016/j.crhy.2019.05.014
%G en
%F CRPHYS_2019__20_4_371_0

Pietro Gravino; Bernardo Monechi; Vittorio Loreto. Towards novelty-driven recommender systems. Comptes Rendus. Physique, Volume 20 (2019) no. 4, pp. 371-379. doi : 10.1016/j.crhy.2019.05.014. https://comptes-rendus.academie-sciences.fr/physique/articles/10.1016/j.crhy.2019.05.014/

Bibliographie
Cité par

[1] E. Bakshy; S. Messing; L.A. Adamic Exposure to ideologically diverse news and opinion on facebook, Science, Volume 348 (2015) no. 6239, pp. 1130-1132

[2] P. Barberá; J.T. Jost; J. Nagler; J.A. Tucker; R. Bonneau Tweeting from left to right: is online political communication more than an echo chamber?, Psychol. Sci., Volume 26 (2015) no. 10, pp. 1531-1542 (PMID: 26297377)

[3] D.E. Berlyne Novelty, complexity, and hedonic value, Percept. Psychophys., Volume 8 (1970) no. 5, pp. 279-286

[4] https://blogs.cornell.edu/info2040/2012/09/20/last-fm-music-reccomendation-incorporating-social-network-ties-and-collaborative-filtering/ (blogs.cornell.edu. Last.fm – Music Recommendation incorporating social network ties and collaborative filtering)

[5] Ò. Celma; P. Cano From hits to niches?: Or how popular artists can bias music recommendation and discovery, Proceedings of the 2nd KDD Workshop on Large-Scale Recommender Systems and the Netflix Prize Competition, ACM, 2008, p. 5

[6] D. Cosley; S.K. Lam; I. Albert; J.A. Konstan; J. Riedl Is seeing believing?: How recommender system interfaces affect users' opinions, Ft. Lauderdale, FL, USA, 5–10 April 2003, ACM, New York (2003), pp. 585-592

[7] United Nations Human Rights Council Report of the Special Rapporteur on the promotion and protection of the right to freedom of opinion and expression https://www.ohchr.org/EN/Issues/FreedomOpinion/Pages/ContentRegulation.aspx

[8] M. Del Vicario; A. Bessi; F. Zollo; F. Petroni; A. Scala; G. Caldarelli; H.E. Stanley; W. Quattrociocchi The spreading of misinformation online, Proc. Natl. Acad. Sci., Volume 113 (2016) no. 3, pp. 554-559

[9] S. Flaxman; S. Goel; J.M. Rao Filter bubbles, echo chambers, and online news consumption, Public Opin. Q., Volume 80 ( 03 2016 ) no. S1, pp. 298-320

[10] World Wide Web Foundation For the web https://fortheweb.webfoundation.org/

[11] P. Gravino; S. Caminiti; A. Sîrbu; F. Tria; V.D.P. Servedio; V. Loreto Unveiling political opinion structures with a web-experiment, COMPLEXIS 2016, Rome, Italy, 22–24 April, 2016, Science and Technology Publications, Lda, Setúbal, Portugal (2016), pp. 39-47

[12] P. Gravino; B. Monechi; V.D.P. Servedio; F. Tria; V. Loreto Crossing the horizon: exploring the adjacent possible in a cultural system, Paris, France, 27 June–1 July 2016 (2016)

[13] K. Hosanagar; D. Fleder; D. Lee; A. Buja Will the global village fracture into tribes? Recommender systems and their effects on consumer fragmentation, Manag. Sci., Volume 60 (2013) no. 4, pp. 805-823

[14] D. Jannach; L. Lerche; F. Gedikli; G. Bonnin What recommenders recommend–an analysis of accuracy, popularity, and sales diversity effects, UMAP 2013, Rome, Italy, 10–14 June 2013 (S. Carberry; S. Weibelzahl; A. Micarelli; G. Semeraro, eds.), Springer (2013), pp. 25-37

[15] S.A. Kauffman Investigations, Oxford University Press, 2000

[16] Y. Koren The Bellkor solution to the Netflix grand prize, Netflix Prize Doc., Volume 81 (2009), pp. 1-10

[17] Y. Koren Collaborative filtering with temporal dynamics, KDD '09, Paris, France, 28 June, 28–1 July 2009, ACM, New York (2009), pp. 447-456

[18] G. Linden; B. Smith; J. York Amazon.com recommendations: item-to-item collaborative filtering, IEEE Internet Comput., Volume 1 (2003) no. 1, pp. 76-80

[19] P. Lops; M. De Gemmis; G. Semeraro Content-based recommender systems: state of the art and trends, Recommender Systems Handbook, Springer, 2011, pp. 73-105

[20] M. McPherson; L. Smith-Lovin; J.M. Cook Birds of a feather: homophily in social networks, Annu. Rev. Sociol., Volume 27 (2001) no. 1, pp. 415-444

[21] B. Monechi; Ã. Ruiz-Serrano; F. Tria; V. Loreto Waves of novelties in the expansion into the adjacent possible, PLoS ONE, Volume 12 (2017) no. 6

[22] T.T. Nguyen; P.-M. Hui; F. Maxwell Harper; L. Terveen; J.A. Konstan Exploring the filter bubble: the effect of using recommender systems on content diversity, WWW '14, Seoul, Korea, 7–11 April 2014, ACM, New York (2014), pp. 677-686

[23] T.P. Novikoff; J.M. Kleinberg; S.H. Strogatz Education of a model student, Proc. Natl. Acad. Sci. USA, Volume 109 (2012) no. 6, pp. 1868-1873

[24] B. Pan; X.R. Li The long tail of destination image and online marketing, Ann. Tour. Res., Volume 38 (2011) no. 1, pp. 132-152

[25] E. Pariser The Filter Bubble: What the Internet Is Hiding From You, Penguin, UK, 2011

[26] G.C. Rodi; V. Loreto; V.D.P. Servedio; F. Tria Optimal learning paths in information networks, Sci. Rep., Volume 5 (2015)

[27] B. Sarwar; G. Karypis; J. Konstan; J. Riedl Item-based collaborative filtering recommendation algorithms, WWW'01, Hong Kong, 1–5 May 2001, ACM, New York (2001), pp. 285-295

[28] J. Ben Schafer; D. Frankowski; J. Herlocker; S. Sen Collaborative filtering recommender systems, The Adaptive Web, Springer, 2007, pp. 291-324

[29] Federal News Service President Obama's farewell address https://www.nytimes.com/2017/01/10/us/politics/obama-farewell-address-speech.html

[30] R.S. Sutton; A.G. Barto Reinforcement Learning: An Introduction, MIT Press, 2018

[31] F. Tria; V. Loreto; V.D.P. Servedio; S.H. Strogatz The dynamics of correlated novelties, Sci. Rep., Volume 4 (2014), p. 5890

[32] R. Zhou; S. Khemmarat; L. Gao The impact of youtube recommendation system on video views, IMC '10, 1–3 November 2010, ACM, New York (2010), pp. 404-410

Frans van der Sluis Wanting information: Uncertainty and its reduction through search engagement, Information Processing Management, Volume 62 (2025) no. 2, p. 103890 | DOI:10.1016/j.ipm.2024.103890
Rabab Ali Abumalloh; Mehrbakhsh Nilashi; Osama Halabi; Raian Ali Does metaverse improve recommendations quality and customer trust? A user-centric evaluation framework based on the cognitive-affective-behavioural theory, Journal of Innovation Knowledge, Volume 9 (2024) no. 4, p. 100569 | DOI:10.1016/j.jik.2024.100569
Giordano De Marzo; Pietro Gravino; Vittorio Loreto Recommender systems may enhance the discovery of novelties, Journal of Physics: Complexity, Volume 5 (2024) no. 4, p. 045008 | DOI:10.1088/2632-072x/ad9cdd
Rahul Shrivastava; Dilip Singh Sisodia; Naresh Kumar Nagwani Multi-stakeholder recommendations system with deep learning-based diversity personalization and multi-objective optimization for establishing trade-off among competing preferences, Kybernetes (2024) | DOI:10.1108/k-02-2024-0344
Stefania Ionescu; Anikó Hannák; Nicolò Pagan The role of luck in the success of social media influencers, Applied Network Science, Volume 8 (2023) no. 1 | DOI:10.1007/s41109-023-00573-4
Stefania Ionescu; Nicolò Pagan; Anikó Hannák Individual Fairness for Social Media Influencers, Complex Networks and Their Applications XI, Volume 1077 (2023), p. 162 | DOI:10.1007/978-3-031-21127-0_14
Alessandro Bellina; Claudio Castellano; Paul Pineau; Giulio Iannelli; Giordano De Marzo Effect of collaborative-filtering-based recommendation algorithms on opinion polarization, Physical Review E, Volume 108 (2023) no. 5 | DOI:10.1103/physreve.108.054304
Perry Zurn; Dani S. Bassett Curiosity and networks of possibility, Possibility Studies Society, Volume 1 (2023) no. 1-2, p. 236 | DOI:10.1177/27538699231168079
Giovanni Emanuele Corazza Beyond the adjacent possible: On the irreducibility of human creativity to biology and physics, Possibility Studies Society, Volume 1 (2023) no. 1-2, p. 37 | DOI:10.1177/27538699221145664
Zheqing Zhu; Benjamin Van Roy, Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (2023), p. 3636 | DOI:10.1145/3583780.3615048
Naieme Hazrati; Francesco Ricci The Impact of Recommender System and Users’ Behaviour on Choices’ Distribution and Quality, Advances in Bias and Fairness in Information Retrieval, Volume 1610 (2022), p. 12 | DOI:10.1007/978-3-031-09316-6_2
Lennart Björneborn Adjacent Possible, The Palgrave Encyclopedia of the Possible (2022), p. 16 | DOI:10.1007/978-3-030-90913-0_100
Wenshuo Guo; Karl Krauth; Michael Jordan; Nikhil Garg, Equity and Access in Algorithms, Mechanisms, and Optimization (2021), p. 1 | DOI:10.1145/3465416.3483298
Madhusree Kuanr; Puspanjali Mohapatra Assessment Methods for Evaluation of Recommender Systems: A Survey, Foundations of Computing and Decision Sciences, Volume 46 (2021) no. 4, p. 393 | DOI:10.2478/fcds-2021-0023
François Fouss; Elora Fernandes A Closer-to-Reality Model for Comparing Relevant Dimensions of Recommender Systems, with Application to Novelty, Information, Volume 12 (2021) no. 12, p. 500 | DOI:10.3390/info12120500
Fernando Ortega; Raúl Lara-Cabrera; Ángel González-Prieto; Jesús Bobadilla Providing reliability in recommender systems through Bernoulli Matrix Factorization, Information Sciences, Volume 553 (2021), p. 110 | DOI:10.1016/j.ins.2020.12.001
Liang Zhang; Xiao Jing Liu A novel recommendation algorithm based on product life cycle theory, Journal of Computational Methods in Sciences and Engineering, Volume 21 (2021) no. 4, p. 969 | DOI:10.3233/jcm-204562
Malte Ostendorff; Corinna Breitinger; Bela Gipp A Qualitative Evaluation of User Preference for Link-Based vs. Text-Based Recommendations of Wikipedia Articles, Towards Open and Trustworthy Digital Societies, Volume 13133 (2021), p. 63 | DOI:10.1007/978-3-030-91669-5_6
Yiping Wen; Feiran Wang; Rui Wu; Jianxun Liu; Buqing Cao Improving the novelty of retail commodity recommendations using multiarmed bandit and gradient boosting decision tree, Concurrency and Computation: Practice and Experience, Volume 32 (2020) no. 14 | DOI:10.1002/cpe.5703
Mengling Ma; Yong Jiang, Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering (2020), p. 616 | DOI:10.1145/3452940.3453060
James E. Cutting Goldilocks Aesthetics, Projections, Volume 14 (2020) no. 2, p. 66 | DOI:10.3167/proj.2020.140206
Lennart Björneborn Adjacent Possible, The Palgrave Encyclopedia of the Possible (2020), p. 1 | DOI:10.1007/978-3-319-98390-5_100-1
Kasra Majbouri Yazdi; Adel Majbouri Yazdi; Saeed Khodayi; Jingyu Hou; Wanlei Zhou; Saeid Saedy; Mehrdad Rostami, 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) (2019), p. 301 | DOI:10.1109/pdcat46702.2019.00062

Cité par 23 documents. Sources : Crossref

Commentaires - Politique