Comments on “NewsBot AI
Tiffany Zhong@tzhongg · something new! @BinaryCap @ProductHunt
I've known @theashbhat for 3 years now and I'm pumped to finally be working on a project with him. Obviously, there's been lots of fake news and political drama happening right now so we decided to build a Facebook bot that has one of the best models in predicting political bias as well as summarizing articles (85% on our sample set but we've changed and i… See more
Ash Bhat@theashbhat · maker and breaker of things
@tzhongg likewise :)
Parker Woodward@parkerwoodward
@tzhongg @theashbhat Nice work! Can't wait to see how this evolves if it does.
John Schenk@johnschenk · Founder at Taffy
@tzhongg @theashbhat This is pretty cool. Now if only you can "neutralize" that bias! 🤣
kurt braget@kurtybot · developer, entrepreneur
Some feedback: out of the 10 articles that I saw, 9 of them were all left liberal biased. I would intro the tool by trying to provide a better mix. A tool of revealing bias shouldn't be so biased, in other words :P As a user, I feel like there would be a lot of friction in having to consult with a bot every time I wanted to view an article's bias. This prod… See more
Ash Bhat@theashbhat · maker and breaker of things
@kurtybot thanks for the feedback Kurt! I think you're referencing the intro which pulls the top news stories from Google News. It's pulling the most popular stories regardless of bias. My hunch is that with the recent news from the Trump administration, left leaning sources are getting more traction (thus the 9/10 of top stories being left biased). We can … See more
Tiffany Zhong@tzhongg · something new! @BinaryCap @ProductHunt
@theashbhat @kurtybot yeah our next step is to build a chrome extension! would be super useful for sure
Jerry Becker@beckerjs · All Around Good Guy
@kurtybot : totally agree with your feedback - especially the chrome plugin idea. eliminate the friction by fully integrating the value of the algorithm into the user's already-existing news reading experience. that would be a great next-step if the bot mvp validates the problem/solution
Alexandre Mouriec@mrcalexandre · Associate @ Argos VR | Writer @ Stuffi
Congrats on the launch @ali_wetrill @theashbhat @tzhongg 👍👏 It's a fantastic way to use a chatbot to help reduce fake news and the spread of fake information. As a French, I don't know very well the bias of every sources so that's also helpful for that. With the French elections recently, your chatbot would have been very useful against fake news😕 As … See more
Ash Bhat@theashbhat · maker and breaker of things
@mrcalexandre yea! Our magic is mostly ML classifiers that we built from scratch. UC Berkeley has an amazing ML course called CS189, and I took Andrew Ng's coursera course (Stanford's equivalent) which is also very good. Outside of that, no real additional tools. It's a pretty straightforward server that gets requests from Facebook and responds via webhooks!… See more
Tiffany Zhong@tzhongg · something new! @BinaryCap @ProductHunt
@mrcalexandre @ali_wetrill @theashbhat thanks for the support alexandre!
Alexandre Mouriec@mrcalexandre · Associate @ Argos VR | Writer @ Stuffi
@theashbhat Thanks so much for your help and for sharing how you built it 😄 Iwill check out Andrew Ng's coursera course
carlos garcia@androidlove · Co-Founder, Internet Missionaries
Need a bot that determines political funding behind political bots like this. 🙃
Ash Bhat@theashbhat · maker and breaker of things
@androidlove haha, we're a bunch of UC Berkeley students that are completely self funded 😄
Leo Daniel@jleodaniel
With the bot giving the user an option to agree with bias alignment, how do you protect it from being trolled?
Ash Bhat@theashbhat · maker and breaker of things
@jleodaniel we have multiple biases to compare the user input to. For example the average domain bias (average of the many articles published), and our classifier's prediction. If it's too far off base and isolated it isn't factored into the rating. We've also found that our users tend to falsely report fake news more often than political leaning. We're also… See more
Rob Wood@rob_wood1
A straight left/right bias axis is way too simplistic for media bias. There are roughly 8 major types of bias in news (arguably more). I like that you're measuring it against a crowd (I think?), but I also agree with the user who suggested this would suit a metadata plugin better than a chat bot.
Ash Bhat@theashbhat · maker and breaker of things
@rob_wood1 we created a ML classifier for political text and trained it on around 16,000 articles. It classifies whether an article is political and then the political leaning. If it's not political, the bot states it. We're also doing things like summaries. I'd love to hear more about about the different types of bias!
Jerry Becker@beckerjs · All Around Good Guy
@theashbhat @rob_wood1 : it seems tricky to validate a solution to 2 problems at once - that people want to know the bias in a political post AND that people want political posts summarized. out of curiosity, what made you decide to tackle both problems at once?
Sahas Katta@sahaskatta · CEO
What was the tech stack you used behind this?
Ash Bhat@theashbhat · maker and breaker of things
@sahaskatta python flask application w/ a mongodb database w/ a classifier created w/ scikit-learn
Jordan Fourcher@jfourcher · Badass from the future
You don't need a bot to see if an article is biased.
Ash Bhat@theashbhat · maker and breaker of things
@jfourcher we do more than that. We check for fake news + give summaries as well 😊
Jordan Fourcher@jfourcher · Badass from the future
@theashbhat I will determine myself if it is fake news. I don't need someone to tell me if it is fake news. I've seen legit articles that have been classified as 'fake news' because of keywords and (unfortunately) political reasons. It is the readers responsibility to be active.
Jerry Becker@beckerjs · All Around Good Guy
@dissolved - someone did it!
Zuhayeer Musa@zuhayeer · Co-founder/CEO - Bash
This is awesome, great work! Love the left center right visuals
Ash Bhat@theashbhat · maker and breaker of things
@zuhayeer thanks Zuhayeer!
Mike Liao@mikeliao97 · UC Berkeley
super cool man! congrats!
Ash Bhat@theashbhat · maker and breaker of things
@mikeliao97 Appreciate it Mike!
William LeGate@williamlegate · CEO, Ponder
I've been using it for several days now… the AI article summaries are very impressive. Congrats to @theashbhat & the team!
Ash Bhat@theashbhat · maker and breaker of things
@williamlegate thanks William!
Sydney Liu@sydney_liu_sl · Co-Founder of Commaful
Really impressive product and team :) Been playing around with it for awhile now and find it super useful! Congrats to @theashbhat!!
Ash Bhat@theashbhat · maker and breaker of things
@sydney_liu_sl Sydney! Thanks man
William Hang@william_hang
awesome stuff here and really important problem!!!
Ash Bhat@theashbhat · maker and breaker of things
@william_hang thanks Will! I appreciate the support :)
Keith Pieper@kpieper876 · VP of Technology, IMM
I really like this. Would love to point my personal RSS feeds in for filtering and summarizing.
Lukas Schwab@lukaspdx
Siiiick––reminds me of some research I read a couple years back that correlated pretty simple bag-of-words analysis with the political leaning (apparent in sponsorship) of legislation. I wonder if there are applications of this in governance.
Rahul Dewan@rahulda1 · Engineer
I really like this product. It's a great idea to show whether sources are trusty, but can you get more fine grained? Perhaps who the author is and whether he or she is reliable? That may be more helpful to promote accurate and unbiased reporting
Ash Bhat@theashbhat · maker and breaker of things
@rahulda1 great idea, definitely can look into building support for this
PartTimeExploradora@valerie_carrera · Part Time Exploradora
YASSS this is something that is very much needed right now!
Oscar@oscarpacaa
This works really well. Awesome tool guys!
Ash Bhat@theashbhat · maker and breaker of things
@oscarpacaa thanks Oscar! I'm happy you like it 😊
Matthew Bordas@matthew_bordas · Arming lawyers with automation & AI.
In a time where the lack of trust in the news has created a void between the people and the media, this unique product fills that void by giving the people a tool to help filter out phony content and instill their trust in the media again. The chat interface is intuitive and its output is very accurate. I'm overall very impressed and hopeful for the future d… See more