Photo by Kenny Eliason on Unsplash
2 Bots that I created to make Twitter Better
Reverse Image Search and Image Text Translation in Twitter
4 min read
Twitter as we know it is a great platform to share, learn and have fun observing the left and right fight :D. While the platform itself is evolving and improving constantly, there are some features that I felt are needed but are not available. That’s where Twitter's APIs came handy. They provide opportunities to try new ideas and add features to twitter in the form of Bots. I found couple of features that I thought could add good value to Twitter:
1. @SearchThisImage - Reverse Image Search in Twitter
There are countless Images shared in Twitter without any more information, without context, without mentioning the source or even worse with wrong context or wrong source. When some accounts share images like this, there are replies asking for What, Where, Who etc. I saw this happening in too many places to ignore. A Reverse Image Bot for Tweeted images made a lot of sense. So, I got into action and @SearchThisImage bot was born. (How I did it is for another day / blog).
After releasing the bot, I started to use it myself. I used it mainly in the Archillect and other accounts where image is shared mostly without context. Users saw it and started following the bot. Currently it has 900+ followers. I see it is being used by tweeples mainly in the below cases: a) To Get more Info This is the case I describe above where there is no or very less information shared in the image tweet itself. Users use the Bot and go to the result web page which shows them some more details. Example1, Example2
b) To Validate the Image Context. Many tweets combine text message with a related image to convey the point better. As Twitter says, Tweets with Images have better reach than tweets without. But the images are sometimes very misleading and provide wrong information. Reverse Searching the image leads them to a website that provides the correct context. Example1, Example2
c) To Credit the actual Creator. Digital Arts like Photographs and Paintings are widely shared in Twitter. We could see some users claim to have created the art explicitly or implicitly; but they haven't actually. It is easy to claim ownership to an unknown audience. This Bot has been useful in validating those claims. Example
Though the current result provides useful information, many times providing just one link is very limiting. I've seen more information is avialable in the subsequent links (Google provides 10 links in the API request). The plan is to publish rest of the links in the webpage www.searchthisimage.com. It will be dynamic page - one for each image.
2. TranslateImgToGDoc - Translate Text in Twitter Images
Twitter has a translation service that uses Google Translate to translate tweets. But what if the tweet's message is contained in an image. This happens more often than we know. With Twitter's 280 characters limit, many organizations, celebrities and Governments share documents in image format to convey longer messages. There is no easy way to translate the message. That’s why I created this Bot Translate Image to Gdoc (I know the name is horrible). It translates the text in any document, pushes to a Google Document and replies to the mentioned tweet with the link to the document. Below is the steps that happen:
- There is a tweet with an image with text.
- A user mentions the Bot and the language to be translated to - Ex. @TranslateToGDoc in English
- The bot fetches the image URL
- Copies the image into a Google Document.
- Gets the texts in the image and pastes in the same document at the top of the document.
- Translates the Pasted Text into the requested language and pastes on the top of the document (pushing down the original text to second from top).
- Shares the Google Document URL with read access to all.
- Replies to the mentioned tweet (step 2)
The process seems complicated for sure. May be there is a better way. But this is what I could do with the technical skill sets that I have and most importantly "It Works and is being used".
Did you find this article valuable?
Support Selva Prakash by becoming a sponsor. Any amount is appreciated!