Pub Date : 2022-06-17DOI: 10.48550/arXiv.2206.09024
Keyu Chen, M. Babaeianjelodar, Yiwen Shi, Kamila Janmohamed, Rupak Sarkar, Ingmar Weber, Thomas Davidson, M. Choudhury, Jonathan Y Huang, S. Yadav, Ashique Khudabukhsh, Preslav Nakov, C. Bauch, O. Papakyriakopoulos, K. Khoshnood, Navin Kumar
We investigate how representations of Syrian refugees (2011-2021) differ across US partisan news outlets. We analyze 47,388 articles from the online US media about Syrian refugees to detail differences in reporting between left- and right-leaning media. We use various NLP techniques to understand these differences. Our polarization and question answering results indicated that left-leaning media tended to represent refugees as child victims, welcome in the US, and right-leaning media cast refugees as Islamic terrorists. We noted similar results with our sentiment and offensive speech scores over time, which detail possibly unfavorable representations of refugees in right-leaning media. A strength of our work is how the different techniques we have applied validate each other. Based on our results, we provide several recommendations. Stakeholders may utilize our findings to intervene around refugee representations, and design communications campaigns that improve the way society sees refugees and possibly aid refugee outcomes.
{"title":"Partisan US News Media Representations of Syrian Refugees","authors":"Keyu Chen, M. Babaeianjelodar, Yiwen Shi, Kamila Janmohamed, Rupak Sarkar, Ingmar Weber, Thomas Davidson, M. Choudhury, Jonathan Y Huang, S. Yadav, Ashique Khudabukhsh, Preslav Nakov, C. Bauch, O. Papakyriakopoulos, K. Khoshnood, Navin Kumar","doi":"10.48550/arXiv.2206.09024","DOIUrl":"https://doi.org/10.48550/arXiv.2206.09024","url":null,"abstract":"We investigate how representations of Syrian refugees (2011-2021) differ across US partisan news outlets. We analyze 47,388 articles from the online US media about Syrian refugees to detail differences in reporting between left- and right-leaning media. We use various NLP techniques to understand these differences. Our polarization and question answering results indicated that left-leaning media tended to represent refugees as child victims, welcome in the US, and right-leaning media cast refugees as Islamic terrorists. We noted similar results with our sentiment and offensive speech scores over time, which detail possibly unfavorable representations of refugees in right-leaning media. A strength of our work is how the different techniques we have applied validate each other. Based on our results, we provide several recommendations. Stakeholders may utilize our findings to intervene around refugee representations, and design communications campaigns that improve the way society sees refugees and possibly aid refugee outcomes.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123219990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19388
Nick Beauchamp
While there have been many efforts to monitor or predict Covid using digital traces such as social media, one of the most distinctive and diagnostically important symptoms of Covid -- anosmia, or loss of smell -- remains elusive due to the infrequency of discussions of smell online. It was recently hypothesized that an inadvertent indicator of this key symptom may be misplaced complaints in Amazon reviews that scented products such as candles have no smell. This paper presents a novel Bayesian vector autoregression model developed to test this hypothesis, finding that "no smell" reviews do indeed reflect changes in US Covid cases even when controlling for the seasonality of those reviews. A series of robustness checks suggests that this effect is also seen in perfume reviews, but did not hold for the flu prior to Covid. These results suggest that inadvertent digital traces may be an important tool for tracking epidemics.
{"title":"\"This Candle Has No Smell\": Detecting the Effect of COVID Anosmia on Amazon Reviews Using Bayesian Vector Autoregression","authors":"Nick Beauchamp","doi":"10.1609/icwsm.v16i1.19388","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19388","url":null,"abstract":"While there have been many efforts to monitor or predict Covid using digital traces such as social media, one of the most distinctive and diagnostically important symptoms of Covid -- anosmia, or loss of smell -- remains elusive due to the infrequency of discussions of smell online. It was recently hypothesized that an inadvertent indicator of this key symptom may be misplaced complaints in Amazon reviews that scented products such as candles have no smell. This paper presents a novel Bayesian vector autoregression model developed to test this hypothesis, finding that \"no smell\" reviews do indeed reflect changes in US Covid cases even when controlling for the seasonality of those reviews. A series of robustness checks suggests that this effect is also seen in perfume reviews, but did not hold for the flu prior to Covid. These results suggest that inadvertent digital traces may be an important tool for tracking epidemics.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121383433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19385
Zachary C. Steinert-Threlkeld, Jungseock Joo
This paper introduces the Multimodal Chile & Venezuela Protest Event Dataset (MMCHIVED). MMCHIVED contains city-day event data using a new source of data, text and images shared on social media. These data enables the improved measurement of theoretically important variables such as protest size, protester and state violence, protester demographics, and emotions. In Venezuela, MMCHIVED records many more protests than existing datasets. In Chile, it records slightly more events than the Armed Conflict Location and Events Dataset (ACLED). These extra events are from small cities far from Caracas and Santiago, an improvement of coverage over datasets that rely on newspapers, and the paper confirms they are true positives. While MMCHIVED covers protest events in Chile and Venezuela, the approach used in the paper is generalizable and could generate protest event data in 107 countries containing 97.14% of global GDP and 82.7% of the world's population.
{"title":"MMCHIVED: Multimodal Chile and Venezuela Protest Event Data","authors":"Zachary C. Steinert-Threlkeld, Jungseock Joo","doi":"10.1609/icwsm.v16i1.19385","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19385","url":null,"abstract":"This paper introduces the Multimodal Chile & Venezuela Protest Event Dataset (MMCHIVED). MMCHIVED contains city-day event data using a new source of data, text and images shared on social media. These data enables the improved measurement of theoretically important variables such as protest size, protester and state violence, protester demographics, and emotions. In Venezuela, MMCHIVED records many more protests than existing datasets. In Chile, it records slightly more events than the Armed Conflict Location and Events Dataset (ACLED). These extra events are from small cities far from Caracas and Santiago, an improvement of coverage over datasets that rely on newspapers, and the paper confirms they are true positives. While MMCHIVED covers protest events in Chile and Venezuela, the approach used in the paper is generalizable and could generate protest event data in 107 countries containing 97.14% of global GDP and 82.7% of the world's population.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"279 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113990967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19310
Prashant Khare, Mladen Karan, Stephen McQuistin, C. Perkins, Gareth Tyson, Matthew Purver, P. Healey, Ignacio Castro
The Internet Engineering Task Force (IETF) has developed many of the technical standards that underpin the Internet. The standards development process followed by the IETF is open and consensus-driven, but is inherently both a social and political activity, and latent influential structures might exist within the community. Exploring and understanding these structures is essential to ensuring the IETF’s resilience and openness. We use network analysis to explore the social graph of IETF participants, based on public email discussions and co-author relationships, and the influence of key contributors. We show that a small core of participants dominates: the top 10% contribute almost half (43.75%) of the emails and come from a relatively small group of organisations. On the other hand, we also find that influence has become relatively more decentralised with time. IETF participants also propose and work on drafts that are either adopted by a working group for further refinement or get rejected at an early stage. Using the social graph features combined with email text features, we perform regression analysis to understand the effect of user influence on the success of new work being adopted by the IETF. Our findings shed useful insights into the behavior of participants across time, correlation between influence and success in draft adoption, and the significance of affiliated organisations in the authorship of drafts.
{"title":"The Web We Weave: Untangling the Social Graph of the IETF","authors":"Prashant Khare, Mladen Karan, Stephen McQuistin, C. Perkins, Gareth Tyson, Matthew Purver, P. Healey, Ignacio Castro","doi":"10.1609/icwsm.v16i1.19310","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19310","url":null,"abstract":"The Internet Engineering Task Force (IETF) has developed many of the technical standards that underpin the Internet. The standards development process followed by the IETF is open and consensus-driven, but is inherently both a social and political activity, and latent influential structures might exist within the community. Exploring and understanding these structures is essential to ensuring the IETF’s resilience and openness. We use network analysis to explore the social graph of IETF participants, based on public email discussions and co-author relationships, and the influence of key contributors. We show that a small core of participants dominates: the top 10% contribute almost half (43.75%) of the emails and come from a relatively small group of organisations. On the other hand, we also find that influence has become relatively more decentralised with time. IETF participants also propose and work on drafts that are either adopted by a working group for further refinement or get rejected at an early stage. Using the social graph features combined with email text features, we perform regression analysis to understand the effect of user influence on the success of new work being adopted by the IETF. Our findings shed useful insights into the behavior of participants across time, correlation between influence and success in draft adoption, and the significance of affiliated organisations in the authorship of drafts.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124390793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19289
Omkar Gurjar, Tanmay Bansal, Hitkul Jangra, Hemank Lamba, P. Kumaraguru
Users often post on content-sharing platforms in the hope of attracting high engagement from viewers. Some posts receive unusual attention and go "viral", eliciting a significant response (likes, views, shares) to the creator in the form of popularity shocks. Past theories have suggested a sense of reputation as one of the key drivers of online activity and the tendency of users to repeat fruitful behaviors. Based on these, we theorize popularity shocks to be linked with changes in the behavior of users. In this paper, we propose a framework to study the changes in user activity in terms of frequency of posting and content posted around popularity shocks. Further, given the sudden nature of their occurrence, we look into the survival durations of effects associated with these shocks. We observe that popularity shocks lead to an increase in the posting frequency of users, and users alter their content to match with the one which resulted in the shock. Also, it is found that shocks are tough to maintain, with effects fading within a few days for most users. High response from viewers and diversification of content posted is found to be linked with longer survival durations of the shock effects. We believe our work fills the gap related to observing users' online behavior exposed to sudden popularity and has widespread implications for platforms, users, and brands involved in marketing on such platforms.
{"title":"Effect of Popularity Shocks on User Behaviour","authors":"Omkar Gurjar, Tanmay Bansal, Hitkul Jangra, Hemank Lamba, P. Kumaraguru","doi":"10.1609/icwsm.v16i1.19289","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19289","url":null,"abstract":"Users often post on content-sharing platforms in the hope of attracting high engagement from viewers. Some posts receive unusual attention and go \"viral\", eliciting a significant response (likes, views, shares) to the creator in the form of popularity shocks. Past theories have suggested a sense of reputation as one of the key drivers of online activity and the tendency of users to repeat fruitful behaviors. Based on these, we theorize popularity shocks to be linked with changes in the behavior of users. In this paper, we propose a framework to study the changes in user activity in terms of frequency of posting and content posted around popularity shocks. Further, given the sudden nature of their occurrence, we look into the survival durations of effects associated with these shocks. We observe that popularity shocks lead to an increase in the posting frequency of users, and users alter their content to match with the one which resulted in the shock. Also, it is found that shocks are tough to maintain, with effects fading within a few days for most users. High response from viewers and diversification of content posted is found to be linked with longer survival durations of the shock effects. We believe our work fills the gap related to observing users' online behavior exposed to sudden popularity and has widespread implications for platforms, users, and brands involved in marketing on such platforms.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130600374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19315
Marianne Aubin Le Quere, Ting-Wei Chiang, Mor Naaman
During the COVID-19 pandemic, local news organizations have played an important role in keeping communities informed about the spread and impact of the virus. We explore how political, social media, and economic factors impacted the way local media reported on COVID-19 developments at a national scale between January 2020 and July 2021. We construct and make available a dataset of over 10,000 local news organizations and their social media handles across the U.S. We use social media data to estimate the population reach of outlets (their “localness”), and capture underlying content relationships between them. Building on this data, we analyze how local and national media covered four key COVID-19 news topics: Statistics and Case Counts, Vaccines and Testing, Public Health Guidelines, and Economic Effects. Our results show that news outlets with higher population reach reported proportionally more on COVID-19 than more local outlets. Separating the analysis by topic, we expose more nuanced trends, for example that outlets with a smaller population reach covered the Statistics and Case Counts topic proportionally more, and the Economic Effects topic proportionally less. Our analysis further shows that people engaged proportionally more and used stronger reactions when COVID-19 news were posted by outlets with a smaller population reach. Finally, we demonstrate that COVID-19 posts in Republican-leaning counties generally received more comments and fewer likes than in Democratic counties, perhaps indicating controversy.
{"title":"Understanding Local News Social Coverage and Engagement at Scale during the COVID-19 Pandemic","authors":"Marianne Aubin Le Quere, Ting-Wei Chiang, Mor Naaman","doi":"10.1609/icwsm.v16i1.19315","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19315","url":null,"abstract":"During the COVID-19 pandemic, local news organizations have played an important role in keeping communities informed about the spread and impact of the virus. We explore how political, social media, and economic factors impacted the way local media reported on COVID-19 developments at a national scale between January 2020 and July 2021. We construct and make available a dataset of over 10,000 local news organizations and their social media handles across the U.S. We use social media data to estimate the population reach of outlets (their “localness”), and capture underlying content relationships between them. Building on this data, we analyze how local and national media covered four key COVID-19 news topics: Statistics and Case Counts, Vaccines and Testing, Public Health Guidelines, and Economic Effects. Our results show that news outlets with higher population reach reported proportionally more on COVID-19 than more local outlets. Separating the analysis by topic, we expose more nuanced trends, for example that outlets with a smaller population reach covered the Statistics and Case Counts topic proportionally more, and the Economic Effects topic proportionally less. Our analysis further shows that people engaged proportionally more and used stronger reactions when COVID-19 news were posted by outlets with a smaller population reach. Finally, we demonstrate that COVID-19 posts in Republican-leaning counties generally received more comments and fewer likes than in Democratic counties, perhaps indicating controversy.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121705747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19358
Huy Vu, Salvatore Giorgi, Jeremy D. W. Clifton, Niranjan Balasubramanian, H. A. Schwartz
How we perceive our surrounding world impacts how we live in and react to it. In this study, we propose LaBel (Latent Beliefs Model), an alternative to topic modeling that uncovers latent semantic dimensions from transformer-based embeddings and enables their representation as generated phrases rather than word lists. We use LaBel to explore the major beliefs that humans have about the world and other prevalent domains, such as education or parenting. Although human beliefs have been explored in previous works, our proposed model helps automate the exploring process to rely less on human experts, saving time and manual efforts, especially when working with large corpus data. Our approach to LaBel uses a novel modification of autoregressive transformers to effectively generate texts conditioning on a vector input format. Differently from topic modeling methods, our generated texts (e.g. “the world is truly in your favor”) are discourse segments rather than word lists, which helps convey semantics in a more natural manner with full context. We evaluate LaBel dimensions using both an intrusion task as well as a classification task of identifying categories of major beliefs in tweets finding greater accuracies than popular topic modeling approaches.
{"title":"Modeling Latent Dimensions of Human Beliefs","authors":"Huy Vu, Salvatore Giorgi, Jeremy D. W. Clifton, Niranjan Balasubramanian, H. A. Schwartz","doi":"10.1609/icwsm.v16i1.19358","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19358","url":null,"abstract":"How we perceive our surrounding world impacts how we live in and react to it. In this study, we propose LaBel (Latent Beliefs Model), an alternative to topic modeling that uncovers latent semantic dimensions from transformer-based embeddings and enables their representation as generated phrases rather than word lists. We use LaBel to explore the major beliefs that humans have about the world and other prevalent domains, such as education or parenting. Although human beliefs have been explored in previous works, our proposed model helps automate the exploring process to rely less on human experts, saving time and manual efforts, especially when working with large corpus data. Our approach to LaBel uses a novel modification of autoregressive transformers to effectively generate texts conditioning on a vector input format. Differently from topic modeling methods, our generated texts (e.g. “the world is truly in your favor”) are discourse segments rather than word lists, which helps convey semantics in a more natural manner with full context. We evaluate LaBel dimensions using both an intrusion task as well as a classification task of identifying categories of major beliefs in tweets finding greater accuracies than popular topic modeling approaches.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122443073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19378
Sviatlana Höhn, S. Mauw, Nicholas M. Asher
New social networks and platforms such as Telegram, Gab and Parler offer a stage for extremist, racist and aggressive content, but also provide a safe space for freedom fighters in authoritarian regimes. Data from such platforms offer excellent opportunities for research on issues such as linguistic bias and toxic language detection. However, only a few, mostly unannotated, English-only corpora from such platforms exist. This article presents a new Telegram corpus in Russian and Belorussian languages tailored for research on linguistic bias in political news. In addition, we created a repository to make all currently available corpora from so-called "dark" platforms accessible in one place.
{"title":"BelElect: A New Dataset for Bias Research from a \"Dark\" Platform","authors":"Sviatlana Höhn, S. Mauw, Nicholas M. Asher","doi":"10.1609/icwsm.v16i1.19378","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19378","url":null,"abstract":"New social networks and platforms such as Telegram, Gab and Parler offer a stage for extremist, racist and aggressive content, but also provide a safe space for freedom fighters in authoritarian regimes. Data from such platforms offer excellent opportunities for research on issues such as linguistic bias and toxic language detection. However, only a few, mostly unannotated, English-only corpora from such platforms exist. This article presents a new Telegram corpus in Russian and Belorussian languages tailored for research on linguistic bias in political news. In addition, we created a repository to make all currently available corpora from so-called \"dark\" platforms accessible in one place.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129367588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19297
Sohyeon Hwang, Aaron Shaw
The governance of many online communities relies on rules created by participants. However, prior work provides limited evidence about how these self-governance efforts compare and relate to one another across communities. Studies tend either to analyze communities as discrete entities or consider communities that coexist within a hierarchically-managed platform. In this paper, we investigate both comparative and relational dimensions of self-governance in similar communities. We use exhaustive trace data from the five largest language editions of Wikipedia over almost 20 years since their founding, and consider both patterns in rule-making and overlaps in rule sets. We find similar rule-making activity across the five communities that replicates and extends prior work on English language Wikipedia alone. However, we also find that these Wikipedias have increasingly unique rule sets, even as editing activity concentrates on rules shared between them. Self-governing communities aligned in key ways may share a common core of rules and rule-making practices as they develop and sustain institutional variations.
{"title":"Rules and Rule-Making in the Five Largest Wikipedias","authors":"Sohyeon Hwang, Aaron Shaw","doi":"10.1609/icwsm.v16i1.19297","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19297","url":null,"abstract":"The governance of many online communities relies on rules created by participants. However, prior work provides limited evidence about how these self-governance efforts compare and relate to one another across communities. Studies tend either to analyze communities as discrete entities or consider communities that coexist within a hierarchically-managed platform. In this paper, we investigate both comparative and relational dimensions of self-governance in similar communities. We use exhaustive trace data from the five largest language editions of Wikipedia over almost 20 years since their founding, and consider both patterns in rule-making and overlaps in rule sets. We find similar rule-making activity across the five communities that replicates and extends prior work on English language Wikipedia alone. However, we also find that these Wikipedias have increasingly unique rule sets, even as editing activity concentrates on rules shared between them. Self-governing communities aligned in key ways may share a common core of rules and rule-making practices as they develop and sustain institutional variations.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"269 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133632125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.1609/icwsm.v16i1.19269
Pinar Barlas, Maximilian Krahn, S. Kleanthous, K. Kyriakou, Jahna Otterbacher
Much attention has been on the behaviors of computer vision services when describing images of people. Audits have revealed rampant biases that could lead to harm, when services are used by developers and researchers. We focus on temporal auditing, replicating experiments originally conducted three years ago. We document the changes observed over time, relating this to the growing awareness of structural oppression and the need to align technology with social values. While we document some positive changes in the services’ behaviors, such as increased accuracy in the use of gender-related tags overall, we also replicate findings concerning larger error rates for images of Black individuals. In addition, we find cases of increased use of inferential tags (e.g., emotions), which are often sensitive. The analysis underscores the difficulty in following changes in services’ behaviors over time, and the need for more oversight of such services.
{"title":"Shifting Our Awareness, Taking Back Tags: Temporal Changes in Computer Vision Services' Social Behaviors","authors":"Pinar Barlas, Maximilian Krahn, S. Kleanthous, K. Kyriakou, Jahna Otterbacher","doi":"10.1609/icwsm.v16i1.19269","DOIUrl":"https://doi.org/10.1609/icwsm.v16i1.19269","url":null,"abstract":"Much attention has been on the behaviors of computer vision services when describing images of people. Audits have revealed rampant biases that could lead to harm, when services are used by developers and researchers. We focus on temporal auditing, replicating experiments originally conducted three years ago. We document the changes observed over time, relating this to the growing awareness of structural oppression and the need to align technology with social values. While we document some positive changes in the services’ behaviors, such as increased accuracy in the use of gender-related tags overall, we also replicate findings concerning larger error rates for images of Black individuals. In addition, we find cases of increased use of inferential tags (e.g., emotions), which are often sensitive. The analysis underscores the difficulty in following changes in services’ behaviors over time, and the need for more oversight of such services.","PeriodicalId":175641,"journal":{"name":"International Conference on Web and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134286099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：