Inspiration
Too many scams nowadays, recent trend in telegram involving unsolicited adding of users into groups or DMs (e.g. asking if you are looking for a job) Messages are becoming more human-like and "friendly", may be harder for people to differentiate between scam or not scam.
What it does
Detects whether a message is a scam or not and informs the user.
How we built it
LSTM model together with FlaskAPI and DialogFlow to make up the telegram bot.
Challenges we ran into
Cleaning of data set us back time-wise as it initially did not work. Challenge in launching the telegram bot
Accomplishments that we're proud of
Successfully launching the telegram bot and achieving desired response from the machine.
What we learned
Learnt how to launch a telegram bot.
What's next for TFScamBot by OOP-C
Perhaps an integration with a social platform as scams are prevalent there as well. Plus with an increasing amount of minors on social platforms, it is important to protect them from such risks.
Built With
- dialogflow
- flaskapi
- glove
- keras
- lstm
- python
- tensorflow
Log in or sign up for Devpost to join the conversation.