Shut Your Mouth API

An API to end cyber bullying 🤐

5 followers

An API to end cyber bullying 🤐

5 followers

Visit website

Unified API

•

AI Metrics and Evaluation

•

AI Content Detection

An API that detects negative/positive sentiments in text and returns a well-structured meaningful interpretation 🙂 💚

Launch tags:Web App•Productivity•API

Launch Team

CloudflareStill paying to deploy your apps? Try Cloudflare Workers for free

Promoted

Secure My Website

The idea is something the world needs and I hope you all will stick together as a team and continue to improve this technology. I agree with a lot of the comments about the nature of the results they're getting with very minimal testing. Perhaps you can add a checkmark on your homepage testing tool to allow people to give you permission to capture that test for the improvement of your platform? I typed in something that was one of the most offensive troubling things a bully said to me as a kid 25 years ago and I remember it to this day: "go back to where you came from" That resulted in Neutral on your API. As you can imagine, that is a troubling thing for a kid to hear, so it will be useful if you can expand your algorithms. I wish you all the best!

Report

8yr ago

Love the idea. How is this better than IBM Watson's Sentiment Analysis? As others have pointed out, something like "My day sucked" would hypothetically be flagged in an app, but it is a way of venting. Whats the plan to handle conversation like venting, etc?

Report

8yr ago

While the idea is impeccable and aims to solve a very real problem - the execution at it's best is less than mediocre. For starters, this project should've first been launch in an alpha stage with a handful of testers before the pricing was outed. Second, this is just negative word detection and does not inculcate sentiment analysis at all. Most chat softwares and forum/message board softwares (wherein such an API would prove useful) include an option to include negative keywords that are banned rendering the use-case for such a third party service obsolete. Secondly, as @altay_akkus pointed out - this does not even get close to identifying the word. It wildcards a string and then regexed the whole of it without taking into consideration word, spaces or carriage returns. Ultimately leading to terms such as "Who" and "How" being marked as insults too. I'll not get into the Privacy and Pricing bit of it. As @altay_akkus covered it. But if you're running a text analytics API against bullying, you should have some sort of ML in the background running at least very basic sentimental analysis. Something very basic that understands expressions or at least makes a basic attempt to understand connotations and innuendo. // Example Friend - Lost my dog today man, feeling too low! Me - That sucks bro. I am sorry for your loss! It'll get better // Your API marks my reply as invalid, wherein I am just trying to tell a friend that I agree with his situation being down, but it'll get better. TL;DR - The product is not ready to ship. A whole lot of issues going on. I have seen your work and admire that you're trying to ship as many products as possible in 2018 - but unfortunately this one needs a lot of work. Right now, it's just a negative word detection API that too incomplete. Take a look at projects like polarity or the Neutrino Bad Word Filter API or something like Textgain.

Report

8yr ago

I'm so excited.Really this API will help all of the peoples to make language more polite.you guys are already build a starting point for the peace full world. <3

Report

8yr ago

TeamWatch

Maker

@shani_weerasinghe Thank you Shani. That's an amazing sentiment & visualization. Appreciate the kind words 🙂

Report

8yr ago

Success with the development! I see a good start, but a lot needs to be done to make it really price worthly. I've tried some sentences which aren't detected, but should for sure.

Report

8yr ago

TeamWatch

Maker

@wouter0100 You are right, there's a lot to do to make it a go-to service for sentiment detection in apps. We are improving it, so hopefully it'll get there soon. Thank you :)

Report

8yr ago

When I type: "You seem cool we should hang out" Your api flags it as "Offensive" because there is the word "ho" in "should". I think this needs a lot more work.

Report

8yr ago