btrantruong's profile picture. Informatics Ph.D student at Indiana University Bloomington

Bao Truong

@btrantruong

Informatics Ph.D student at Indiana University Bloomington

Bao Truong أعاد

Our team just launched three new tools to help you explore social media data: 🌉NewsBridge – Adds AI-powered context to Facebook posts 🔎Barney’s Tavern – Search 34B social media posts 🌎OSoMeNet – Visualize how info spreads across platforms osome.iu.edu/research/blog/…


New preprint! 🚀 We looked into the rise of Bluesky and found that this platform is definitely sticking around 🚀 Huge kudos to my amazing co-authors for digging through nearly two years of all Bluesky data!

Paper alert! 🚨 We investigate Bluesky from an invitation only platform with a few thousands of users to reaching 30 million users in terms of user activity and network. 📄 Full paper: arxiv.org/abs/2504.12902 💻 Codes: github.com/osome-iu/rise_… 💾 Dataset: zenodo.org/records/150660…



Bao Truong أعاد

New paper in PNAS: Fact-checking information from large language models can decrease headline discernment What are the unintended consequences of AI fact-checking? Even LLMs that accurately identify false headlines can actually cause harm. doi.org/10.1073/pnas.2…

OSoMe_IU's tweet image. New paper in PNAS: Fact-checking information from large language models can decrease headline discernment

What are the unintended consequences of AI fact-checking? Even LLMs that accurately identify false headlines can actually cause harm.

doi.org/10.1073/pnas.2…

Bao Truong أعاد

🚨Our new paper is on arXiv! We’re excited to share 26 state-backed information operation (IO) datasets, each paired with a robust control set of 13M+ posts in total from non-IO accounts. You can reach the dataset here: zenodo.org/records/141891… ...


Bao Truong أعاد

Out now in PNAS and led by the amazing @Abdulshir with a great team from @arc_mpib @mpib_berlin, our systematic meta-analysis of individual factors for misinformation susceptibility: pnas.org/doi/10.1073/pn…


Bao Truong أعاد

Our new working paper shows how a single choice by many social media platforms—to treat all resharing as if from the original poster—can drastically reshape our understanding of the social dynamics on those platforms. doi.org/10.48550/arXiv…

mdeverna2's tweet image. Our new working paper shows how a single choice by many social media platforms—to treat all resharing as if from the original poster—can drastically reshape our understanding of the social dynamics on those platforms.

doi.org/10.48550/arXiv…

Bao Truong أعاد

Our letter & accompanying news article + editorial in @ScienceMagazine question the unwarranted conclusion generally drawn by the media and science community (as well as Meta) about a positive role of the Facebook ranking algorithm on misinformation 🧪 Details in the 🧵 below...

Science published our eLetter, along with an editorial & article discussing its implications. In it, we call into question a widely reported Science paper, funded by Meta, which suggested that Facebook's news feed algorithm prevents misinformation. science.org/content/articl… 🧵1/7

science.org

A study found Facebook’s algorithm didn’t promote political polarization. Critics have doubts

Letter to Science questions experiment done during 2020 U.S. elections



Bao Truong أعاد

OSoMe Awesome Speakers returns next week! We're starting off strong with a talk from Josephine (Jo) Lukito, "Challenges and Solutions for Multi-Platform Studies of Election Discourse" Register here: iu.zoom.us/meeting/regist…

OSoMe_IU's tweet image. OSoMe Awesome Speakers returns next week!

We're starting off strong with a talk from Josephine (Jo) Lukito, "Challenges and Solutions for Multi-Platform Studies of Election Discourse"

Register here: iu.zoom.us/meeting/regist…

Bao Truong أعاد

AI search engines use LLMs to summarize results for you, but can LLMs discern low-credibility sources from credible ones? Our paper measures the accuracy of LLMs' credibility ratings on news sources and political biases. With @OSoMe_IU 🔗arxiv.org/abs/2304.00228 1/9

yang3kc's tweet image. AI search engines use LLMs to summarize results for you, but can LLMs discern low-credibility sources from credible ones? Our paper measures the accuracy of LLMs' credibility ratings on news sources and political biases.

With @OSoMe_IU
🔗arxiv.org/abs/2304.00228  
1/9
yang3kc's tweet image. AI search engines use LLMs to summarize results for you, but can LLMs discern low-credibility sources from credible ones? Our paper measures the accuracy of LLMs' credibility ratings on news sources and political biases.

With @OSoMe_IU
🔗arxiv.org/abs/2304.00228  
1/9
yang3kc's tweet image. AI search engines use LLMs to summarize results for you, but can LLMs discern low-credibility sources from credible ones? Our paper measures the accuracy of LLMs' credibility ratings on news sources and political biases.

With @OSoMe_IU
🔗arxiv.org/abs/2304.00228  
1/9

Bao Truong أعاد

Our latest @PNASNexus paper compares harms when fake accts infiltrate communities, flood the network, & target individuals: Quantifying the vulnerabilities of the online public square to adversarial manipulation tactics doi.org/10.1093/pnasne… 🧪w/@btrantruong X Lou, A Flammini

OSoMe_IU's tweet image. Our latest @PNASNexus paper compares harms when fake accts infiltrate communities, flood the network, & target individuals:

Quantifying the vulnerabilities of the online public square to adversarial manipulation tactics
doi.org/10.1093/pnasne…

🧪w/@btrantruong X Lou, A Flammini

I can attest to this. Great thread👇 Bonus meme by @Shugars

btrantruong's tweet image. I can attest to this. Great thread👇 

Bonus meme by @Shugars

I recently attended @IC2S2's tutorial "Training Computational Social Science PhD Students for Academic and Non-Academic Careers" Tutorial Website: github.com/jaeyk/ic2s2-tr… A 🧵 with some unique tips/tricks/perspectives I picked up that may be helpful for other students...



I will be adding a session for Background/Keyword/Problem in my future posters — found it super helpful to get a quick grasp of a work & spark conversations. Some examples from #ic2s2 Last one is an amazing work by @arianna_pera1 and @lajello

btrantruong's tweet image. I will be adding a session for Background/Keyword/Problem in my future posters — found it super helpful to get a quick grasp of a work & spark conversations. Some examples from #ic2s2
Last one is an amazing work by @arianna_pera1 and @lajello
btrantruong's tweet image. I will be adding a session for Background/Keyword/Problem in my future posters — found it super helpful to get a quick grasp of a work & spark conversations. Some examples from #ic2s2
Last one is an amazing work by @arianna_pera1 and @lajello
btrantruong's tweet image. I will be adding a session for Background/Keyword/Problem in my future posters — found it super helpful to get a quick grasp of a work & spark conversations. Some examples from #ic2s2
Last one is an amazing work by @arianna_pera1 and @lajello

#sicss and #ic2s2 wrapped! Been an amazing 2 weeks at Penn. It was a great pleasure meeting people from different in fields, learning about all the cool work in the CSS space, finally meeting collaborators in flesh, hosting a tutorial with my colleagues and presenting my work 🤩

btrantruong's tweet image. #sicss and #ic2s2 wrapped! 
Been an amazing 2 weeks at Penn. It was a great pleasure meeting people from different in fields, learning about all the cool work in the CSS space, finally meeting collaborators in flesh, hosting a tutorial with my colleagues and presenting my work 🤩
btrantruong's tweet image. #sicss and #ic2s2 wrapped! 
Been an amazing 2 weeks at Penn. It was a great pleasure meeting people from different in fields, learning about all the cool work in the CSS space, finally meeting collaborators in flesh, hosting a tutorial with my colleagues and presenting my work 🤩
btrantruong's tweet image. #sicss and #ic2s2 wrapped! 
Been an amazing 2 weeks at Penn. It was a great pleasure meeting people from different in fields, learning about all the cool work in the CSS space, finally meeting collaborators in flesh, hosting a tutorial with my colleagues and presenting my work 🤩

Bao Truong أعاد

This looks like a rap album cover 😂

We are at ic2s2! First conf trip since 2020….!! @haewoon

JisunAn's tweet image. We are at ic2s2! First conf trip since 2020….!! @haewoon


Bao Truong أعاد

📢 If you are at @ic2s2, join us for our tutorial “Exploring Emerging Social Media: Acquiring, Processing, and Visualizing Data with Python and OSoMe Web Tools.” 📅 Time: 9 AM – 12:30 PM 📍Location: Irvine: Amado Recital Hall ℹ️Details: osome.iu.edu/events/ic2s2-2… 1/2


Bao Truong أعاد

A lot has happened over the past couple of months... 🚀 ICYMI, our paper "Identifying and characterizing superspreaders of low credibility content on Twitter" was published in @PLOSOne (open access link below)! 1/8


Bao Truong أعاد

Misinformation posted to Twitter comes from 'superspreader' accounts, say researchers, amid warnings for future of content moderation on X Reporting on latest paper w/@mdeverna2 @RachithAiyappa @diogofpacheco @jb_tweets 🧪 doi.org/10.1371/journa… abc.net.au/news/2024-05-2…


Bao Truong أعاد

Excited to share our latest work, "Symmetry breaking in optimal transport networks," just out in @Naturecomms! 🚀 This was a fantastic collaboration with @filrad, @santo, @siragerkol, and Marc. Here's a short thread summarizing our main findings! 1/8

The best subway line that one can build with a fixed budget could be one serving only half of the population! Check out our paper just out in @NatureComms. @filrad @Sid_Patwardhan_ @siragerkol @IULuddy rdcu.be/dGSxA



Bao Truong أعاد

Emergence of simple and complex contagion dynamics from weighted belief networks | Science Advances science.org/doi/10.1126/sc… Awesome work led by @RachithAiyappa 👏👏


Bao Truong أعاد

.@IC2S2 Excited to announce that our tutorial "Exploring Emerging Social Media" is part of #IC2S2 2024! 🌐 Thanks @OSoMe_IU @yang3kc @waying_zhao @btrantruong. See you there! More info coming soon.


Loading...

Something went wrong.


Something went wrong.