Dezembro 2022 vol. 10 num. 5 - 14º Congresso Brasileiro de Pesquisa e Desenvolvimento em Design

Artigo - Open Access.

Idioma principal | Segundo idioma

A transparência de sistemas de recomendação de plataformas de Vídeo sob Demanda (VoD): categorias de conteúdos

Transparency of Video on Demand (VoD) platforms recommender systems: content categories

RUIZ, Cinthia ; QUARESMA, Manuela ;

Artigo:

Este artigo objetiva investigar a transparência do sistema de recomendação de plataformas de vídeo sob demanda baseado em Inteligência Artificial e Aprendizado de Máquina. Com os algoritmos cada vez mais presentes em nossas vidas e trazendo mudanças de interação, faz-se necessário o olhar sobre a experiência de uso. A falta de transparência dos algoritmos acarreta problemas para o usuário, como modelo mental inadequado, dificuldades para o controle do sistema e falta de confiança nas recomendações. Foi realizado, então, um estudo por meio de um workshop de design para envolver usuários e designers em possíveis soluções com Explainable AI. Como resultado, foram apontadas oportunidades para melhorar a explicabilidade das recomendações.

Artigo:

This article aims to investigate the transparency of video-on-demand platforms recommender system based on Artificial Intelligence and Machine Learning. With algorithms increasingly present in our lives and bringing changes in interaction, it is necessary to look at the experience of use. The lack of transparency of the algorithms causes problems for the user, such as an inadequate mental model, difficulties in controlling the system and lack of confidence in the recommendations. A study was then carried out through a design workshop to involve users and designers in possible solutions with Explainable AI. As a result, opportunities were identified to improve the explainability of the recommendations.

Download (PDF)

Palavras-chave: Experiência do Usuário; Transparência; Aprendizado de máquina.,

Palavras-chave: User Experience; Transparency; Machine Learning.,

DOI: 10.5151/ped2022-1591479

Referências bibliográficas
  • [1] BUDIU, R. Can Users Control and Understand a UI Driven by Machine Learning? 2018. Disponível em: . Acesso em: 22 nov. 2020.
  • [2] CRAMER, H.; THORN, J. Not-So-Autonomous, Very Human Decisions in Machine Learning: Questions when Designing for ML. AAAI Spring Symposium – Technical Report, 2017. V. SS-17-01-, p. 412–414.
  • [3] FERREIRA, J. J.; MONTEIRO, M. S. What Are People Doing About XAI User Experience? A Survey on AI Explainability Research and Practice. In: MARCUS, A.; ROSENZWEIG, E. (Org.). 9th International Conference on Design, User Experience, and Usability (DUXU 2020). Cham: Springer, 2020, p. 56–7
  • [4] FLI FUTURE OF LIFE INSTITUTE. Asilomar AI Principles. 2017. Disponível em: . Acesso em: 7 maio 2020.
  • [5] GILPIN, L. H. et al. Explaining explanations: An overview of interpretability of machine learning. Proceedings – 2018 IEEE 5th International Conference on Data Science and Advanced Analytics, DSAA 2018, 2019. P. 80–89.
  • [6] GOMEZ-URIBE, C. A.; HUNT, N. The Netflix Recommender System: Algorithms, Business Value, and Innovation. ACM Transactions on Management Information Systems, v. 6, n. 4, 2015.
  • [7] GOOGLE PAIR. People + AI Guidebook. 2019. Disponível em: . Acesso em: 7 maio 2020.
  • [8] JANSSON, D. G.; SMITH, S. M. Design fixation. Design Studies, v. 12, n. 1, p. 3–11, jan. 1991.
  • [9] JIN, W. et al. Bridging ai developers and end users: An end-user-centred explainable ai taxonomy and visual vocabularies. Proceedings of the IEEE Visualization, Vancouver, BC, Canada, 201 p. 20-25.
  • [10] KONSTAN, J. A.; RIEDL, J. Recommender Systems: From Algorithms to User Experience. User Modeling and User-Adapted Interaction, 2012. V. 22, n. 1–2, p. 101–123.
  • [11] LAMY, J. B. et al. Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach. Artificial Intelligence in Medicine, 2019. V. 94, n. August 2018, p. 42–53.
  • [12] LE, H. et al. Measuring political personalization of Google news search. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Anais...Association for Computing Machinery, Inc, 13 maio 2019.
  • [13] MARTIN, B.; HANINGTON, B. Universal Methods of Design: 100 Ways to Research Complex Problems, Develop Innovative Ideas, and Design Effective Solutions. Beverly: Rockport Publishers, 2012.
  • [14] MICROSOFT. Microsoft AI Principles. 2018. Disponível em: . Acesso em: 7 maio 2020.
  • [15] MINISTRY OF INTERNAL AFFAIRS AND COMMUNICATIONS (MIC), The G. Of J. AI R&D Principles. 2017.
  • [16] OECD COUNCIL RECOMMENDATION ON ARTIFICIAL INTELLIGENCE. OECD Principles on AI. 2019. Disponível em: . Acesso em: 7 maio 2020.
  • [17] OXBOROUGHT, C. et al. Explainable AI: Driving business value throught greater understandin. [S.l.]: [s.n.], 2018.
  • [18] RIBERA, M.; LAPEDRIZA, A. Can we do better explanations? A proposal of User-Centered Explainable AI. New York: ACM, 2019. p. 7.
  • [19] ROUHIAINEN, L. Artificial Intelligence: 101 Things You Must Know Today About Our Future. [S.l.]: [s.n.], 2018.
  • [20] SAMEK, W.; WIEGAND, T.; MÜLLER, K.-R. Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models. 2017.
  • [21] SAMIH, A.; ADADI, A.; BERRADA, M. Towards a knowledge based Explainable Recommender Systems. ACM International Conference Proceeding Series, 2019.
  • [22] TINTAREV, N.; MASTHOFF, J. Explaining Recommendations: Design and Evaluation. Recommender Systems Handbook. Boston, MA: Springer US, 2015, p. 353–382.
  • [23] WANG, Pei. What Do You Mean by “AI”? Frontiers in Artificial Intelligence and Applications 171(1):362-373, 2008. In: Conference: Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference, 2008
  • [24] WEITZ, K. et al. “Let me explain!”: exploring the potential of virtual agents in explainable AI interaction design. Journal on Multimodal User Interfaces, 2020.
  • [25] XU, F. et al. Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges. In: TANG, J. et al. (Org.). Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019 Dunhuang, China, October 9–14, 2019 Proceedings, Part II. Dunhuang: Springer, 2019, p. 563–574.
Como citar:

RUIZ, Cinthia; QUARESMA, Manuela; "A transparência de sistemas de recomendação de plataformas de Vídeo sob Demanda (VoD): categorias de conteúdos", p. 1609-1624 . In: Anais do 14º Congresso Brasileiro de Pesquisa e Desenvolvimento em Design. São Paulo: Blucher, 2022.
ISSN 2318-6968, DOI 10.5151/ped2022-1591479

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações