An official website of the United States government
Social media streams analysis can reveal the characteristics of people who engage with or write about different topics. Recent works show that it is possible to reveal sensitive attributes (e.g., location, gender, ethnicity, political views, etc.) of individuals by analyzing their social media streams. Although, the prediction of a user's sensitive attributes can be used to enhance the user experience in social media, revealing some attributes like the location could represent a threat on individuals. Users can obfuscate their location by posting about random topics linked to different locations. However, posting about random and sometimes contradictory topics that are not aligned with a user's online persona and posts could negatively affect the followers interested in her profile. This paper represents our vision about the future of user privacy on social media. Users can locally deploy a cyborg, an artificial intelligent system that helps people to defend their privacy on social media. We propose LocBorg, a location privacy preserving cyborg that protects users by obfuscating their location while maintaining their online persona. LocBorg analyzes the social media streams and recommends topics to write about that are similar to a user's topics of interest and aligned with the user's online persona but linked to other locations.
more »
« less
Location Prediction with Communities in User Ego-Net in Social Media
Social media embed rich but noisy signals of physical locations of their users. Accurately inferring a user's location can significantly improve the user's experience on the social media and enable the development of new location-based applications. This paper proposes a novel community-based approach for predicting the location of a user by using communities in the egonet of the user. We further propose both geographical proximity and structural proximity metrics to profile communities in the ego-net of a user, and then evaluate the effectiveness of each individual metric on real social media data. We discover that geographical proximity metrics, such as average/median haversine distance and community closeness, are strong indicators of a good community for geotagging. In addition, structural proximity metric conductance performs comparable to geographical proximity metrics while triangle participation ratio and internal density are weak location indicators. To the best of our knowledge, this is the first effort to infer the physical location of a user from the perspective of latent communities in the user's ego-net.
more »
« less
- Award ID(s):
- 1737861
- PAR ID:
- 10177409
- Date Published:
- Journal Name:
- ICC 2019 - 2019 IEEE International Conference on Communications (ICC)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Rapid restoration of access to essential goods and services has long been regarded as paramount for community recovery. Yet, there remains ambiguity in how access should be defined, measured, or operationalized. Defining accessibility as the ability to use available goods and services with a reasonable level of effort and cost requires evaluating it across six dimensions (proximity,availability,adequacy,acceptability,affordability, andawareness) while considering the perspective of both users and providers in the evaluation. But common distance-based metrics that focus solely on physical access and travel time often fall short of fully capturing these requirements, overlooking the user's perception. This paper introduces a new spatio-temporal accessibility metric that combines four out of these six dimensions, including proximity, acceptability, adequacy, and availability. The metric considers uncertainty in measuring each dimension and addresses both user and provider perspectives in measuring the acceptability and adequacy dimensions. The variation in the metric across the disaster timeline serves as a proxy for community recovery. The metric aligns with common engineering-oriented functionality-based resilience frameworks as the functionality level of the providers has been incorporated in its development. Operating at the household level, the metric determines the ratio of post-disruption access time to the intended good or service against its pre-disruption access time and yields a unitless ratio between zero and one, with zero expressing a total loss in accessibility and one signifying the same level of accessibility as pre-disruption. The proposed metric, while being scientifically principled, is a practical tool whose output is easily understood even by non-expert individuals. The metric is illustrated for schools and pharmacies using the Lumberton Testbed and data collected following the 2016 flood in Lumberton, North Carolina after Hurricane Matthew. Findings provide new insight into recovery plan prioritization and can be used to trigger protective actions. The paper concludes by discussing issues and barriers related to developing and validating accessibility metrics while highlighting areas for future research.more » « less
-
Towards the vision of building artificial intelligence systems that can assist with our everyday life, we introduce a proof of concept for a social media privacy "cyborg" which can locally and privately monitor a person's published content and offer advice or warnings when their privacy is at stake. The idea of a cyborg can be more general, as a separate local entity with its own computational resources, that can automatically perform several online tasks on our behalf. For this demonstration, we assume an attacker that can successfully infer user attributes, solely based on what the user has published (topic-based inference). We focus on Social Media privacy and specifically on the issue of exposing sensitive user-attributes, like location, or race, through published content. We built a privacy cyborg that can monitor a user's posted topics and automatically warn them in real time when a sensitive attribute is at risk of being exposed.more » « less
-
Social media feed ranking algorithms fail when they too narrowly focus on engagement as their objective. The literature has asserted a wide variety of values that these algorithms should account for as well -- ranging from well-being to productive discourse -- far more than can be encapsulated by a single topic or theory. In response, we present a library of values for social media algorithms: a pluralistic set of 78 values as articulated across the literature, implemented into LLM-powered content classifiers that can be installed individually or in combination for real-time re-ranking of social media feeds. We investigate this approach by developing a browser extension, Alexandria, that re-ranks the X/Twitter feed in real time based on the user's desired values. Through two user studies, both qualitative (N=12) and quantitative (N=257), we found that diverse user needs require a large library of values, enabling more nuanced preferences and greater user control. With this work, we argue that the values criticized as missing from social media ranking algorithms can be operationalized and deployed today through end-user tools.more » « less
-
Prejudice and hate directed toward Asian individuals has increased in prevalence and salience during the COVID-19 pandemic, with notable rises in physical violence. Concurrently, as many governments enacted stay-at-home mandates, the spread of anti-Asian content increased in online spaces, including social media. In the present study, we investigated temporal and geographical patterns in social media content relevant to anti-Asian prejudice during the COVID-19 pandemic. Using the Twitter Data Collection API, we queried over 13 million tweets posted between January 30, 2020, and April 30, 2021, for both negative (e.g., #kungflu) and positive (e.g., #stopAAPIhate) hashtags and keywords related to anti-Asian prejudice. In a series of descriptive analyses, we found differences in the frequency of negative and positive keywords based on geographic location. Using burst detection, we also identified distinct increases in negative and positive content in relation to key political tweets and events. These largely exploratory analyses shed light on the role of social media in the expression and proliferation of prejudice as well as positive responses online.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICC.2019.8761695
