Maximizing the Diversity of Exposure in a Social Network

Matakos, Antonis; Aslay, Çiğdem; Galbrun, Esther; Gionis, Aristides

doi:10.1109/tkde.2020.3038711

Cited by 16 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches could be considered to take into account the frequency of the events or the diversity of opinions presented or give more relevance to extreme events, which may be more accurately detected and evaluated. In particular, the value of being exposed to multiple opinions (time-aggregated CE) may be augmented with a measure of diversity (e.g., entropy) (Garimella et al, 2017 ; Matakos et al, 2022 ).…”

Section: Defining a Collective Well-being Metric For Social Mediamentioning

confidence: 99%

Challenging social media threats using collective well-being-aware recommendation algorithms and an educational virtual companion

Ognibene¹,

Taibi²,

Kruschwitz³

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

Social media have become an integral part of our lives, expanding our interlinking capabilities to new levels. There is plenty to be said about their positive effects. On the other hand, however, some serious negative implications of social media have been repeatedly highlighted in recent years, pointing at various threats to society and its more vulnerable members, such as teenagers, in particular, ranging from much-discussed problems such as digital addiction and polarization to manipulative influences of algorithms and further to more teenager-specific issues (e.g., body stereotyping). The impact of social media—both at an individual and societal level—is characterized by the complex interplay between the users' interactions and the intelligent components of the platform. Thus, users' understanding of social media mechanisms plays a determinant role. We thus propose a theoretical framework based on an adaptive “Social Media Virtual Companion” for educating and supporting an entire community, teenage students, to interact in social media environments in order to achieve desirable conditions, defined in terms of a community-specific and participatory designed measure of Collective Well-Being (CWB). This Companion combines automatic processing with expert intervention and guidance. The virtual Companion will be powered by a Recommender System (CWB-RS) that will optimize a CWB metric instead of engagement or platform profit, which currently largely drives recommender systems thereby disregarding any societal collateral effect. CWB-RS will optimize CWB both in the short term by balancing the level of social media threats the users are exposed to, and in the long term by adopting an Intelligent Tutor System role and enabling adaptive and personalized sequencing of playful learning activities. We put an emphasis on experts and educators in the educationally managed social media community of the Companion. They play five key roles: (a) use the Companion in classroom-based educational activities; (b) guide the definition of the CWB; (c) provide a hierarchical structure of learning strategies, objectives and activities that will support and contain the adaptive sequencing algorithms of the CWB-RS based on hierarchical reinforcement learning; (d) act as moderators of direct conflicts between the members of the community; and, finally, (e) monitor and address ethical and educational issues that are beyond the intelligent agent's competence and control. This framework offers a possible approach to understanding how to design social media systems and embedded educational interventions that favor a more healthy and positive society. Preliminary results on the performance of the Companion's components and studies of the educational and psychological underlying principles are presented.

show abstract

Section: Defining a Collective Well-being Metric For Social Mediamentioning

confidence: 99%

Challenging social media threats using collective well-being-aware recommendation algorithms and an educational virtual companion

Ognibene¹,

Taibi²,

Kruschwitz³

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…To support tolerance for divergent values, we suggest that social media platforms develop algorithms that recommend new connections who differ in perspective‐enhancing ways. For example, researchers have developed a novel algorithm to increase the “diversity exposure level” of social media users by considering their openness to sharing ideologically‐diverse information (Matakos et al 2020). Similarly, recommender engines could identify users who bridge ideological divides and increase their visibility in friend recommendation systems.…”

Section: Social Media Paradoxesmentioning

confidence: 99%

The role of wisdom in navigating social media paradoxes: Implications for consumers, firms, and public policy

Schneider

Chugani

Kaur

et al. 2022

Journal of Consumer Affairs

View full text Add to dashboard Cite

Social media has transformed the nature of communication and simultaneously given rise to paradoxesirresolvable situations where contradictory elements co-exist. These paradoxes are pervasive, and they can jeopardize consumer welfare because they are difficult to navigate. In this conceptual article, we argue that the principles of wisdom provide a unique and constructive lens through which to view the social media landscape with the aim of maximizing well-being. We illustrateThe first five authors led the writing and development of this manuscript. The remaining five contributors are listed alphabetically.

show abstract

“…Note that in order to promote exposition to a diverse set of opinions, these elements (particularly TCE) may contain a measure of diversity of the contents (e.g. entropy) over the dimension specific to the term under consideration (Matakos et al, 2020;Garimella et al, 2017). Indeed, current affective state estimators and toxic content detectors can only provide noisy estimation of the current user state and the content quality.…”

Section: Toward Collective Well-being Measures For Social Mediamentioning

confidence: 99%

“…One example of an educational objective also involving the CWB-RS could be breaking the filter bubbles focused on racist content and helping users hold an unbiased mindset. In this case, the connected content selection strategy will be countering the bubble suggesting content providing opposite but not confrontational perspectives (Garimella et al, 2017;Matakos et al, 2020;Bozdag and van den Hoven, 2015). This strategy can be combined with educational games proposing specifically themed challenges, such as finding pictures of achievements performed by people of different ethnicities, suggesting changing the recommender filter parameters directly, or just reducing the racist content presented and substituting it with low harm feeds.…”

Section: Socialmedia Companion For Collective Well-beingmentioning

confidence: 99%

“…Moving to actual end-users, teenage students, they produce data resembling that from standard social media platforms. Although estimating the level of toxicity and the user's condition from such content is challenging (see Section 5.4), the CWB-RS aims to balance the students' experience and monitor their behaviors (Garimella et al, 2017;Matakos et al, 2020) and interactions to involve parents and educators when eventually needed.…”

Section: Diverse Internal and External Contentmentioning

confidence: 99%

See 1 more Smart Citation

Challenging Social Media Threats using Collective Well-being Aware Recommendation Algorithms and an Educational Virtual Companion

Ognibene¹,

Taibi²,

Kruschwitz³

et al. 2021

Preprint

View full text Add to dashboard Cite

Social media have become an integral part of our lives, expanding our inter-linking capabilities to new levels. There is plenty to be said about their positive effects. On the other hand, however, some serious negative implications of social media have been repeatedly highlighted in recent years, pointing at various threats for society and its more vulnerable members, such as teenagers, in particular, ranging from much-discussed problems such as digital addiction and polarization to manipulative influences of algorithms and further to more teenager-specific issues (e.g. body stereotyping). The full impact of current social media platform design -both at an individual and societal level -asks for a more holistic approach to tackle the problems conceptually. The way forward we see is to extend measures of Collective Well-Being (CWB) to social media communities. As users' relationships and interactions are a central component of CWB, education is crucial to improve CWB. We thus propose a framework based on an adaptive "social media virtual companion" for educating and supporting an entire community, teenage students, to interact with social media. This companion combines automatic processing with expert intervention and guidance. The virtual companion will be powered by a Recommender System (CWB-RS) that will optimize a CWB metric instead of engagement or platform profit, which currently largely drives recommender systems thereby disregarding any societal collateral effect. CWB-RS will optimize 1

show abstract

Maximizing the Diversity of Exposure in a Social Network

Cited by 16 publications

References 34 publications

Challenging social media threats using collective well-being-aware recommendation algorithms and an educational virtual companion

Challenging social media threats using collective well-being-aware recommendation algorithms and an educational virtual companion

The role of wisdom in navigating social media paradoxes: Implications for consumers, firms, and public policy

Challenging Social Media Threats using Collective Well-being Aware Recommendation Algorithms and an Educational Virtual Companion

Contact Info

Product

Resources

About