Tootfinder

Chesebro hid from Michigan investigators secret Twitter account he used to promote election conspiracy theories - National Zero
https://nationalzero.com/2024/02/27/chesebro-hid-sec…

ThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents
Hoang-Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
#SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.

Persistent Homology generalizations for Social Media Network Analysis
Isabela Rocha
https://arxiv.org/abs/2404.19257 https://arxiv.org/pdf/2404.19257
arXiv:2404.19257v1 Announce Type: new
Abstract: This study details an approach for the analysis of social media collected political data through the lens of Topological Data Analysis, with a specific focus on Persistent Homology and the political processes they represent by proposing a set of mathematical generalizations using Gaussian functions to define and analyze these Persistent Homology categories. Three distinct types of Persistent Homologies were recurrent across datasets that had been plotted through retweeting patterns and analyzed through the k-Nearest-Neighbor filtrations. As these Persistent Homologies continued to appear, they were then categorized and dubbed Nuclear, Bipolar, and Multipolar Constellations. Upon investigating the content of these plotted tweets, specific patterns of interaction and political information dissemination were identified, namely Political Personalism and Political Polarization. Through clustering and application of Gaussian density functions, I have mathematically characterized each category, encapsulating their distinctive topological features. The mathematical generalizations of Bipolar, Nuclear, and Multipolar Constellations developed in this study are designed to inspire other political science digital media researchers to utilize these categories as to identify Persistent Homology in datasets derived from various social media platforms, suggesting the broader hypothesis that such structures are bound to be present on political scraped data regardless of the social media it's derived from. This method aims to offer a new perspective in Network Analysis as it allows for an exploration of the underlying shape of the networks formed by retweeting patterns, enhancing the understanding of digital interactions within the sphere of Computational Social Sciences.

The Wayback Machine never forgets...
"The BadgerPundit account went private sometime in late 2022, but CNN was able to access the since-removed public tweets by using the Wayback Machine, an internet archive."
Exclusive: Key figure in fake electors plot concealed damning posts on secret Twitter account from investigators
https://www.cnn.com/2024/02/26/politics/kenneth-chesebro-secret-twitter-account-kfile/index.html

Screenshotted this past tweet of mine from April 3rd in case some of the people who I removed are wondering why they're no longer following me and can no longer see my tweets on-site:

This https://arxiv.org/abs/2402.13452 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems. In this study, we present a new framework to surveil public health, focusing on mental health (MH) outcomes. We hypothesize that locally posted tweets are indicative of local MH outcomes and collect tweets posted from 765 neighborhoods (census block groups) in the USA. We pair these tweets from each neighborhood with the corresponding MH outcome reported …

Users invented retweets.
They typed “RT” and then pasted in the text of a tweet they liked. The practice became so widespread that Twitter turned it into an official feature.
Quote-tweets were created by Twitter users, too: they typed a commentary on someone else’s tweet, then pasted in the URL of that tweet. Voila, the quote-tweet was born.
And users invented tweet-threading: the first Twitter threads were created by posting a tweet, then replying to your own tweet, then r…

Huh... I didn't realize that somewhere along the way X restricted access to public tweets/posts to logged-in users.
I noticed this when viewing X profiles from a browser where I was NOT logged in. Then I went to https://twitter.com/danyork - all it showed me was my one pinned tweet (amusingly…

Dan York (@danyork) on X
Working for open Internet for everyone. #InternetAccess, #LEOs, #curling, #Vermont. Work: @InternetSociety. Still tweeting, but also at @danyork@mastodon.social

🤖 Generator-Guided Crowd Reaction Assessment
(... I was really fascinated with this paper because my YOShInOn RSS reader has a module like this which can predict the popularity of a story on HN and if people will have a big discussion about it; it is super-easy to gather data for this kind of model)
https://arxiv.org/abs/2403.0…

Generator-Guided Crowd Reaction Assessment
In the realm of social media, understanding and predicting post reach is a significant challenge. This paper presents a Crowd Reaction AssessMent (CReAM) task designed to estimate if a given social media post will receive more reaction than another, a particularly essential task for digital marketers and content writers. We introduce the Crowd Reaction Estimation Dataset (CRED), consisting of pairs of tweets from The White House with comparative measures of retweet count. The proposed Generator…

I was reminiscing last week about our previous MP. James Lunney was a Reform/Conservative MP and he was 'famous’ for saying dumb anti-science things. He was also a chiropractor... which tracks. He was the only politician on Twitter to block me. He didn't like his constituents asking him how his ancestors walked with T-Rex I guess. 🤷‍♂️
Here's the blast from the past:

A friend sent this to me and y'all might enjoy

If anyone had ever wondered why I followed @sassycrass (RIP) over on Twitter* here’s just one reminder from back in 2022: Another Mask Incident
*That’s a Trick Question - I can’t imagine anyone wondering that.

Huh... I didn't realize that somewhere along the way X restricted access to public tweets/posts to logged-in users.
I noticed this when viewing X profiles from a browser where I was NOT logged in. Then I went to https://twitter.com/danyork - all it showed me was my one pinned tweet (amusingly…

Dan York (@danyork) on X
Working for open Internet for everyone. #InternetAccess, #LEOs, #curling, #Vermont. Work: @InternetSociety. Still tweeting, but also at @danyork@mastodon.social

LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
Vijeta Deshpande, Minhwa Lee, Zonghai Yao, Zihao Zhang, Jason Brian Gibbons, Hong Yu
https://arxiv.org/abs/2402.13452

LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems. In this study, we present a new framework to surveil public health, focusing on mental health (MH) outcomes. We hypothesize that locally posted tweets are indicative of local MH outcomes and collect tweets posted from 765 neighborhoods (census block groups) in the USA. We pair these tweets from each neighborhood with the corresponding MH outcome reported …

From Adoption to Adaption: Tracing the Diffusion of New Emojis on Twitter
Yuhang Zhou, Xuan Lu, Wei Ai
https://arxiv.org/abs/2402.14187 https://

From Adoption to Adaption: Tracing the Diffusion of New Emojis on Twitter
In the rapidly evolving landscape of social media, the introduction of new emojis in Unicode release versions presents a structured opportunity to explore digital language evolution. Analyzing a large dataset of sampled English tweets, we examine how newly released emojis gain traction and evolve in meaning. We find that community size of early adopters and emoji semantics are crucial in determining their popularity. Certain emojis experienced notable shifts in the meanings and sentiment associ…

"NBC News identified 33 instances, starting in November 2020, when people or institutions singled out by Libs of TikTok later reported bomb threats or other violent intimidation. The threats, which on average came several days after tweets from Libs of TikTok, targeted schools, libraries, hospitals, small businesses and elected officials in 16 states, Washington, D.C., and...Ontario. Twenty-one of the 33 threats were bomb threats, which most commonly targeted schools..."

After Libs of TikTok posted, at least 21 bomb threats followed
Libs of TikTok, run by Chaya Raichik, has gained immense popularity on X. As her follower-count has risen, bomb threats targeting her subjects followed.

Revealed: How a mysterious social media account is influencing Congress - Alternet.org
https://www.alternet.org/christian-mike-johnson/?utm_medium=email

Revealed: How a mysterious social media account is influencing Congress
On X, formerly Twitter, @ringwiss has at least 14,000 followers and regularly tweets about the United States' congressional procedures. Many X users have wondered who @ringwiss is, and according to Politico's Gabe Fleisher, he isn't from the U.S., but rather, is Kacper Surdy — a 20-year-old economic...

Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance
Rachith Aiyappa, Shruthi Senthilmani, Jisun An, Haewoon Kwak, Yong-Yeol Ahn
https://arxiv.org/abs/2403.00236

Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance
We investigate the performance of LLM-based zero-shot stance detection on tweets. Using FlanT5-XXL, an instruction-tuned open-source LLM, with the SemEval 2016 Tasks 6A, 6B, and P-Stance datasets, we study the performance and its variations under different prompts and decoding strategies, as well as the potential biases of the model. We show that the zero-shot approach can match or outperform state-of-the-art benchmarks, including fine-tuned models. We provide various insights into its performa…

Indicators for characterising online hate speech and its automatic detection
Erica Forzinetti, Marco L. Della Vedova, Stefano Pasta, Milena Santerini
https://arxiv.org/abs/2402.08462

Indicators for characterising online hate speech and its automatic detection
We examined four case studies in the context of hate speech on Twitter in Italian from 2019 to 2020, aiming at comparing the classification of the 3,600 tweets made by expert pedagogists with the automatic classification made by machine learning algorithms. Pedagogists used a novel classification scheme based on seven indicators that characterize hate. These indicators are: the content is public, it affects a target group, it contains hate speech in explicit verbal form, it will not redeem, it …

Indicators for characterising online hate speech and its automatic detection
Erica Forzinetti, Marco L. Della Vedova, Stefano Pasta, Milena Santerini
https://arxiv.org/abs/2402.08462

Indicators for characterising online hate speech and its automatic detection
We examined four case studies in the context of hate speech on Twitter in Italian from 2019 to 2020, aiming at comparing the classification of the 3,600 tweets made by expert pedagogists with the automatic classification made by machine learning algorithms. Pedagogists used a novel classification scheme based on seven indicators that characterize hate. These indicators are: the content is public, it affects a target group, it contains hate speech in explicit verbal form, it will not redeem, it …

Political polarisation in turbulent times: Tracking polarisation trends and partisan news link sharing on Finnish Twitter, 2015-2023
Antti Gronow, Arttu Malkam\"aki
https://arxiv.org/abs/2403.03842

Political polarisation in turbulent times: Tracking polarisation trends and partisan news link sharing on Finnish Twitter, 2015-2023
The study analyses polarisation on Finnish social media with data from the platform X, which was known as Twitter during the time of data collection (during the Sipilä and Marin governments, 2015-2023). The users were clustered into three different ideological groups - the Conservative Right, the Moderate Right, and the Liberal Left - based on their retweeting of tweets referring to the different political parties in Finland. Trends in polarisation of several topics encompassing the most recen…