An official website of the United States government
Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%.
more »
« less
Keyword expansion techniques for mining social movement data on social media
Abstract Political and social scientists have been relying extensively on keywords such as hashtags to mine social movement data from social media sites, particularly Twitter. Yet, prior work demonstrates that unrepresentative keyword sets can lead to flawed research conclusions. Numerous keyword expansion methods have been proposed to increase the comprehensiveness of keywords, but systematic evaluations of these methods have been lacking. Our paper fills this gap. We evaluate five diverse keyword expansion techniques (or pipelines) on five representative social movements across two distinct activity levels. Our results guide researchers who aim to use social media keyword searches to mine data. For instance, we show that word embedding-based methods significantly outperform other even more complex and newer approaches when movements are in normal activity periods. These methods are also less computationally intensive. More importantly, we also observe that no single pipeline can identify little more than half of all movement-related tweets when these movements are at their peak mobilization period offline. However, coverage can increase significantly when more than one pipeline is used. This is true even when the pipelines are selected at random.
more »
« less
- Award ID(s):
- 1815875
- PAR ID:
- 10367142
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- EPJ Data Science
- Volume:
- 11
- Issue:
- 1
- ISSN:
- 2193-1127
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Existing studies of social movement organizations (SMOs) commonly focus only on a small number of well-known SMOs or SMOs that belong to a single social movement industry (SMI). This is partially because current methods for identifying SMOs are labor-intensive. In contrast to these manual approaches, in our article, we use Twitter data pertaining to BlackLivesMatter and Women’s movements and employ crowdsourcing and nested supervised learning methods to identify more than 50K SMOs. Our results reveal that the behavior and influence of SMOs vary significantly, with half having little influence and behaving in similar ways to an average individual. Furthermore, we show that collectively, small SMOs contributed to the sharing of more diverse information. However, on average, large SMOs were significantly more committed to movements and decidedly more successful at recruiting. Finally, we also observe that a large number of SMOs from an extensive set of SMIs, including Occupy Wall Street, participated in solidarity or even as leaders in BlackLivesMatter. In comparison, few SMIs participated in Women’s movement.more » « less
-
Abstract We analyze social media activity during one of the largest protest mobilizations in US history to examine ideological asymmetries in the posting of news content. Using an unprecedented combination of four datasets (tracking offline protests, social media activity, web browsing, and the reliability of news sources), we show that there is no evidence of unreliable sources having any prominent visibility during the protest period, but we do identify asymmetries in the ideological slant of the sources shared on social media, with a clear bias towards right-leaning domains. These results support the “amplification of the right” thesis, which points to the structural conditions (social and technological) that lead to higher visibility of content with a partisan bent towards the right. Our findings provide evidence that right-leaning sources gain more visibility on social media and reveal that ideological asymmetries manifest themselves even in the context of movements with progressive goals.more » « less
-
Social media enables activists to directly communicate with the public and provides a space for movement leaders, participants, bystanders, and opponents to collectively construct and contest narratives. Focusing on Twitter messages from social movements surrounding three issues in 2018-2019 (guns, immigration, and LGBTQ rights), we create a codebook, annotated dataset, and computational models to detect diagnostic (problem identification and attribution), prognostic (proposed solutions and tactics), and motivational (calls to action) framing strategies. We conduct an in-depth unsupervised linguistic analysis of each framing strategy, and uncover cross-movement similarities in associations between framing and linguistic features such as pronouns and deontic modal verbs. Finally, we compare framing strategies across issues and other social, cultural, and interactional contexts. For example, we show that diagnostic framing is more common in replies than original broadcast posts, and that social movement organizations focus much more on prognostic and motivational framing than journalists and ordinary citizens.more » « less
-
When social movement organizations receive extensive newspaper coverage, why is it sometimes substantive and sometimes not? By “substantive,” we mean coverage that reflects serious treatment of the movement's issues, demands, or policy claims. Scholars agree that the news media are key to movement organizations' influence, helping them alter public discourse and effect political change, but often find that protests are covered nonsubstantively. Employing insights from literatures on historical institutionalism, the social organization of the news, and the consequences of movements, we elaborate an “institutional mediation” model that identifies the interactive effects on coverage of news institutions' operating procedures, movement organizations' characteristics and action, and political contexts. Although movement actors suffer compound legitimacy deficits with journalists, the institutional mediation model identifies the openings news institutions provide, the movement organizational characteristics, the forms of collective action likely to induce substantive news treatment, and the political contexts that will amplify or dampen these effects. We derive four interactive hypotheses from this model, addressing the effects of organizational identities, collective action, and political contexts on news outcomes. We appraise the hypotheses with comparative and qualitative comparative analyses of more than 1000 individually coded articles discussing the five most-covered organizations of the 1960s U.S. civil rights movement across four national newspapers. We find support for each hypothesis and discuss the implications for other movement organizations and the current media context.more » « less
