Smart discord chatbot integrated with Dialogflow to manage different classrooms and assist in teaching!

Overview

smart-school-chatbot

Intro

Smart discord chatbot integrated with Dialogflow to interact with students naturally and manage different classes in a school.

Description

As an effort to manage different classrooms, this smart chatbot is created so students can interact with it on Discord naturally and get things done without TAs or instructors' help.

This chatbot is named Bu, a real name of a dog living in CoderSchool.

Here are what Bu can do:

  • Bu can check your attendance by greeting it.
  • Bu can give important links (material links, zoom link, score dashboard,...)
  • Bu can cheers you up when you are sad :((
  • Bu can tell you jokes to make you smile :))
  • Bu can clear up its own messages.
  • Bu can show who is missing in the class or not yet check their attendance.
  • Bu can answer common questions about CoderSchool (opening hours, who is CEO, best instructor, TA,...)
  • Bu can do small talks to you :))
  • Bu can introduce a bit about itself.
  • Bu can choose what kind of food you should have for lunch or dinner if you are indecisive.
  • Bu can give points to you (Can only be done by TAs/Instructors).

Getting Started

Requirements & Dependencies

  • All the library requirements can be installed through requirements.txt.
pip install -r requirements.txt
  • Make sure you have your own discord details in .env file.
DISCORD_TOKEN={BOT DISCORD TOKEN}
DISCORD_GUILD={GUILD NAME}
COHORT_METADATA={METADATA SPREADSHEET ID}
BOT_NAME={BOT NAME}
STUDENT_SCORING={STUDENT SCORING SPREADSHEET ID}
  • Your Google Service Account credentials in the credentials.json and dialogflow_bot.json.

Workflow

Workflow

This chatbot is running 24/7 to answer questions from students so I choose to host it for free on replit.com and have uptimerobot.com to ping the server every 5 minute to prevent it from shutting down on replit.

Usage

Here are some real examples during the lectures of the chatbot in action where students just talk to it naturally like to a real TA, where its answers are unique and different everytime:

  • Ask what it can do

Help

  • Ask who it is

Who are you?

  • Ask who is the creator of it

Father

  • It can automatically check students' attendance to the system by just greeting to it and it will reply in a funny way

Check attendance 1

Check attendance 2

Check attendance 3

  • It can award students who are active in the class

Give score

As you can see, the bot will automatically log in students' performances like attendance, activities and more. Students can check out their scores and ranking anytime on the Google Data Studio dashboard.

dashboard

  • It can answer some common questions about the course or the company

opening hours

  • It can show relevant links of the course which students ask for

Links

  • It can cheer up students if they are are sad or struggled

Sad cheer up

  • It can tell different jokes

Joke 1

Joke 2

Joke 3

  • It can pick a meal for you if you are indecisive what to have for lunch or dinner (A lot of students request for this feature!)

Meal choice

Acknowledgments

Some useful documents are:

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Owner
Tom Huynh
A Machine Learning Scientist and Engineer!
Tom Huynh
Data preprocessing rosetta parser for python

datapreprocessing_rosetta_parser I've never done any NLP or text data processing before, so I wanted to use this hackathon as a learning opportunity,

ASReview hackathon for Follow the Money 2 Nov 28, 2021
Super easy library for BERT based NLP models

Fast-Bert New - Learning Rate Finder for Text Classification Training (borrowed with thanks from https://github.com/davidtvs/pytorch-lr-finder) Suppor

Utterworks 1.8k Dec 27, 2022
TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (S

InstaDeep Ltd 72 Dec 09, 2022
Final Project for the Intel AI Readiness Boot Camp NLP (Jan)

NLP Boot Camp (Jan) Synopsis Full Name: Prameya Mohanty Name of your School: Delhi Public School, Rourkela Class: VIII Title of the Project: iTransect

TheCodingHub 1 Feb 01, 2022
Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.

Seq2Seq Speech in JAX A JAX/Flax repository for combining a pre-trained speech encoder model (e.g. Wav2Vec2, HuBERT, WavLM) with a pre-trained text de

Sanchit Gandhi 21 Dec 14, 2022
Use AutoModelForSeq2SeqLM in Huggingface Transformers to train COMET

Training COMET using seq2seq setting Use AutoModelForSeq2SeqLM in Huggingface Transformers to train COMET. The codes are modified from run_summarizati

tqfang 9 Dec 17, 2022
Source code of the "Graph-Bert: Only Attention is Needed for Learning Graph Representations" paper

Graph-Bert Source code of "Graph-Bert: Only Attention is Needed for Learning Graph Representations". Please check the script.py as the entry point. We

14 Mar 25, 2022
Text Classification in Turkish Texts with Bert

You can watch the details of the project on my youtube channel Project Interface Project Second Interface Goal= Correctly guessing the classification

42 Dec 31, 2022
A Python wrapper for simple offline real-time dictation (speech-to-text) and speaker-recognition using Vosk.

Simple-Vosk A Python wrapper for simple offline real-time dictation (speech-to-text) and speaker-recognition using Vosk. Check out the official Vosk G

2 Jun 19, 2022
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language mod

13.2k Jul 07, 2021
skweak: A software toolkit for weak supervision applied to NLP tasks

Labelled data remains a scarce resource in many practical NLP scenarios. This is especially the case when working with resource-poor languages (or text domains), or when using task-specific labels wi

Norsk Regnesentral (Norwegian Computing Center) 850 Dec 28, 2022
PyJPBoatRace: Python-based Japanese boatrace tools 🚤

pyjpboatrace :speedboat: provides you with useful tools for data analysis and auto-betting for boatrace.

5 Oct 29, 2022
The simple project to separate mixed voice (2 clean voices) to 2 separate voices.

Speech Separation The simple project to separate mixed voice (2 clean voices) to 2 separate voices. Result Example (Clisk to hear the voices): mix ||

vuthede 31 Oct 30, 2022
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge This is an implementation of the paper,

Mutian He 19 Oct 14, 2022
🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

floret: fastText + Bloom embeddings for compact, full-coverage vectors with spaCy floret is an extended version of fastText that can produce word repr

Explosion 222 Dec 16, 2022
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources Description This is the repository for the paper Unifying Cross-

Sapienza NLP group 16 Sep 09, 2022
Speach Recognitions

easy_meeting Добро пожаловать в интерфейс сервиса автопротоколирования совещаний Easy Meeting. Website - http://cf5c-62-192-251-83.ngrok.io/ Принципиа

Maksim 3 Feb 18, 2022
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Poincaré Embeddings for Learning Hierarchical Representations PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations

Facebook Research 1.6k Dec 29, 2022
A flask application to predict the speech emotion of any .wav file.

This is a speech emotion recognition app. It will allow you to train a modular MLP model with the RAVDESS dataset, and then use that model with a flask application to predict the speech emotion of an

Aryan Vijaywargia 2 Dec 15, 2021
A multi-voice TTS system trained with an emphasis on quality

TorToiSe Tortoise is a text-to-speech program built with the following priorities: Strong multi-voice capabilities. Highly realistic prosody and inton

James Betker 2.1k Jan 01, 2023