Suchergebnisse

Image recognition algorithms that automatically tag or moderate content are crucial in many applications but are increasingly opaque. Given transparency concerns, we focus on understanding how algorithms tag people images and their inferences on attractiveness. Theoretically, attractiveness has an evolutionary basis, guiding mating behaviors, although it also drives social behaviors. We test image-tagging APIs as to whether they encode biases surrounding attractiveness. We use the Chicago Face Database, containing images of diverse individuals, along with subjective norming data and objective facial measurements. The algorithms encode biases surrounding attractiveness, perpetuating the stereotype that "what is beautiful is good." Furthermore, women are often misinterpreted as men. We discuss the algorithms' reductionist nature, and their potential to infringe on users' autonomy and well-being, as well as the ethical and legal considerations for developers. Future services should monitor algorithms' behaviors given their prevalence in the information ecosystem and influence on media. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 810105 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

There are increasing expectations that algorithms should behave in a manner that is socially just. We consider the case of image tagging APIs and their interpretations of people images. Image taggers have become indispensable in our information ecosystem, facilitating new modes of visual communication and sharing. Recently, they have become widely available as Cognitive Services. But while tagging APIs offer developers an inexpensive and convenient means to add functionality to their creations, most are opaque and proprietary. Through a cross-platform comparison of six taggers, we show that behaviors differ significantly. While some offer more interpretation on images, they may exhibit less fairness toward the depicted persons, by misuse of gender-related tags and/or making judgments on a person's physical appearance. We also discuss the difficulties of studying fairness in situations where algorithmic systems cannot be benchmarkedagainst a ground truth. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 810105 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

Image analysis algorithms have been a boon to personalization in digital systems and are now widely available via easy-to-use APIs. However, it is important to ensure that they behave fairly in applications that involve processing images of people, such as dating apps. We conduct an experiment to shed light on the factors influencing the perception of "fairness." Participants are shown a photo along with two descriptions (human- and algorithm-generated). They are then asked to indicate which is "more fair" in the context of a dating site, and explain their reasoning. We vary a number of factors, including the gender, race and attractiveness of the person in the photo. While participants generally found human-generated tags to be more fair, API tags were judged as being more fair in one setting - where the image depicted an "attractive," white individual. In their explanations, participants often mention accuracy, as well as the objectivity/subjectivity of the tags in the description. We relate our work to the ongoing conversation about fairness in opaque tools like image tagging APIs, and their potential to result in harm. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

We are witnessing a movement towards Democratizing AI, with a wide variety of tools, platforms and data sources becoming accessible to more people. This movement is said to be fueling innovation, extending the capabilities of individuals and organizations, by making the creation and application of AI easier. However, beyond the hype, there is a need to understand what this trend means for various stakeholders. Through the lens of socio-political democracy, this chapter examines the democratization of AI. We find that the present state of the "AI Democracy" maps onto only one of three elements of a democracy. Current efforts focus primarily on providing people with the tools and technical infrastructure needed to participate in AI, but not in protecting their freedoms and access to social benefits, which are the other core elements of democracy. We discuss the possibilities for realizing a broader AI democracy, along with the anticipated challenges.

Data attained through crowdsourcing have an essential role in the development of computer vision algorithms. Crowdsourced data might include reporting biases, since crowdworkers usually describe what is "worth saying" in addition to images' content. We explore how the unprecedented events of 2020, including the unrest surrounding racial discrimination, and the COVID-19 pandemic, might be reflected in responses to an open-ended annotation task on people images, originally executed in 2018 and replicated in 2020. Analyzing themes of Identity and Health conveyed in workers' tags, we find evidence that supports the potential for temporal sensitivity in crowdsourced data. The 2020 data exhibit more race-marking of images depicting non-Whites, as well as an increase in tags describing Weight. We relate our findings to the emerging research on crowdworkers' moods. Furthermore, we discuss the implications of (and suggestions for) designing tasks on proprietary platforms, having demonstrated the possibility for additional, unexpected variation in crowdsourced data due to significant events. ; This project is partially funded by the Cyprus Research and Innovation Foundation under grant EXCELLENCE/0918/0086 (DESCANT) and by the European Union's Horizon 2020 Research and Innovation Programme under agreements No. 739578 (RISE) and 810105 (CyCAT).

Image tagging APIs, offered as Cognitive Services in the movement to democratize AI, have become popular in applications that need to provide a personalized user experience. Developers can easily incorporate these services into their applications; however, little is known concerning their behavior under specific circumstances. We consider how two such services behave when predicting elements of the Big-Five personality traits from users' profile images. We found that personality traits are not equally represented in the APIs' output tags, with tags focusing mostly on Extraversion. The inaccurate personality prediction and the lack of vocabulary for the equal representation of all personality traits, could result in unreliable implicit user modeling, resulting in sub-optimal – or even undesirable – user experience in the application.

While crowdsourcing provides a convenient solution for tap- ping into human intelligence, a concern is the bias inherent in the data collected. Events related to the COVID-19 pandemic had an impact on people globally, and crowdworkers were no exception. Given the evidence concerning mood and stress on work, we explore how temporal events might affect crowdsourced data. We replicated an image annotation task conducted in 2018, in which workers describe people images. We expected 2020 annotations to contain more references to health, as compared to 2018 data. Overall, we find no evidence that health-related tags were used more often in 2020, but instead we find a significant increase in the use of tags related to weight (e.g., fat, chubby, overweight). This result, coupled with the "stay at home" act in effect in 2020, illustrate how crowdwork is impacted by temporal events. ; This project is partially funded by the Cyprus Research and Innovation Foundation under grant EXCELLENCE/0918/0086 (DESCANT) and by the European Union's Horizon 2020 Research and Innovation Programme under agreements No. 739578 (RISE), 810105 (CyCAT).

Over the last several years, research on our elected officials' use of social media as a political communication platform has greatly increased. While the bulk of social media-related research focuses on elections, social media-traditional media connections, or the effect of politicians' social media communications on people's attitudes and opinions, the present study shows how members of the U.S. Congress use Twitter to engage in a range of speech-based actions. Examples of these speech-based actions include narration about one's day or recent events, providing information in the form of online or offline information, and positioning for/against policies and other politicians. In terms of outcomes, this paper provides updates regarding gender, chamber, and party-based differences. Second, based on the assumption that speech acts now occur in hybrid form, this paper examines how polarizing political communications are couched in more subdued formats. Third, a set of recommendations is provided to help journalists and citizens identify these hybrid speech-based actions before making a potentially misinformed retweet or comment. In this way, the function of Twitter use by elected officials is further explained and our understanding of Twitter's role in U.S. political communication is further deepened. ; https://deepblue.lib.umich.edu/bitstream/2027.42/145592/1/Updates to Congressional Speech Acts on Twitter - APSA 2018.pdf ; 50 ; 56

Public officials' communication has been explored at length in terms of how such their statements are conveyed in the traditional media, but minimal research has been done to examine their communication via social media. This paper explores the kinds of statements U.S. officials are making on Twitter in terms of the actions they are trying to achieve. We then analyze the correlation between these statements, Congressional communication network structures, and voting behavior. Our analysis leverages over 29,000 tweets by members of Congress in conjunction with existing DW-NOMINATE voting behavior data. We find that pro-social and self-promoting statements correlate with Congressional voting records but that position within the Congressional communication network does not correlate with voting behavior. ; Sponsorship: Social Networks Research Group at IIT, IIT Graduate College

As Twitter becomes a more common means for officials to communicate with their constituents, it becomes more important that we understand just how that communication relates to other political activities. Using data from 411 members of Congress' Twitter activity during the summer of 2011, we examine relationships among the resulting conversation networks, language use, and political behavior. The social networks that result from their communications have surprisingly low density and high diameter, indicating a level of independence that is surprising for a group so tightly connected offline. Our findings also indicate that officials frequently use Twitter to advertise their political positions and to provide information but rarely to request political action from their constituents or to recognize the good work of others. Our analysis suggests strong relationships between anti-social behaviors indicated by the loosely connected network and low incidence of pro-social conversations and polarized or extreme Congressional voting records.

Enthusiasts propose that social media promotes vertical political communication, giving citizens the opportunity to interact directly with their representatives. However, skeptics claim that politicians avoid direct engagement with constituents, using technology to present a façade of interactivity instead. This study explores if and how elected officials in three regions of the world are using Twitter to interact with the public. We examine the Twitter activity of 15 officials over a period of six months. We show that in addition to the structural features of Twitter that are designed to promote interaction, officials rely on language to foster or to avoid engagement. It also provides yet more evidence that the existence of interactive features does not guarantee interactivity.

This paper uses data from 1,042 tweets posted by or mentioning Chicago Aldermen or Mayor Rahm Emanuel to examine how Chicago politicians use social media. Twitter provides a public communication medium in which constituents and their representatives can have two-way conversations that others can witness and record, and we used qualitative and social network methods to examine conversations between Chicagoans and representatives in city government. We coded the contents of each tweet over the two-week time period (e.g., official business, fundraising) and created representations of the social networks created by the users' following behaviors. These networks indicate who receives politicians' tweets and help identify the audiences for political messaging in social media. Our analysis indicates that Chicago's Aldermen and Mayor use Twitter for social conversations more often than political ones, and that only a small number of Aldermen dominate the resulting conversation networks. ; Sponsorship: Social Network Research Group at IIT, IIT Graduate College

As Twitter becomes a more common means for officials to communicate with their constituents, it becomes more important that we understand how officials use these communication tools. Using data from 380 members of Congress' Twitter activity during the winter of 2012, we find that officials frequently use Twitter to advertise their political positions and to provide information but rarely to request political action from their constituents or to recognize the good work of others. We highlight a number of differences in communication frequency between men and women, Senators and Representatives, Republicans and Democrats. We provide groundwork for future research examining the behavior of public officials online and testing the predictive power of officials' social media behavior.