Laroo-Pece Division, Gulu City, Northern Uganda
Uganda time
+256-779-712-990 Learner login Chat on WhatsApp
Lumina Africa Foundation Igniting Light, Inspiring Change.
Donate
Artificial intelligence - Intermediate

Chatbots and Natural Language Processing for Africa

Learn how computers work with human language, why African languages need more attention, and how to design, build, test…

About this course

Every day, millions of people in Africa write messages, send voice notes and ask questions in languages such as Luganda, Swahili, English, Kinyarwanda and many more. Natural language processing (NLP) is the field that teaches computers to work with that language: to count words, sense feelings, find names, translate and answer questions. A chatbot is one of the most useful ways to put NLP to work, because it can answer common questions at any hour on a channel people already use.

This intermediate course starts with the building blocks of NLP in plain words, then looks at why most African languages have far less data and tools than English, and what communities are doing about it. You will learn how to design a chatbot on paper first (goals, users, channels, intents, conversation flows, hand-off to a human), how to write a knowledge base, how to build a simple bot with a free no-code tool, and how to try a short beginner Python example. Then you will test with real users, measure success, and protect privacy, consent and accessibility.

The course ends with a capstone: a bilingual FAQ chatbot design and prototype for a school, clinic or small business. The skills are about thinking and design, so they stay useful as tools change.

What you will learn

  • Explain in plain words what NLP is and describe tokens, text cleaning, sentiment, classification, named entities, translation and speech
  • Count words and run a simple sentiment check on short messages
  • Explain why many African languages are under-resourced and describe community-led responses
  • Judge the ethics of collecting and using language data, including consent and fair credit
  • Design a chatbot with clear goals, users, channels, intents, entities and conversation flows
  • Choose between rule-based, retrieval and generative bots for a given job
  • Write a clear knowledge base and FAQ in simple language, with a safe fallback and hand-off to a person
  • Build and test a simple FAQ chatbot, and measure it with resolution rate and satisfaction
  • Protect privacy, obtain consent and make a chatbot accessible to all users

Course content

5 modules · 17 lessons · 5 h 15 min · 6 quizzes

Module 1: How computers work with language4 lessons

Meet the building blocks of NLP: tokens, cleaning, counting, sentiment, classification, entities, translation and speech.

  1. What NLP is and how text becomes data 15 min
  2. Cleaning text and counting words 15 min
  3. Sentiment, classification and named entities 20 min
  4. Translation and speech technology 15 min
  5. Quiz: 6 questions
Module 2: African languages and NLP3 lessons

See why many African languages have little data, how communities are building it, and how to treat language data ethically.

  1. Why African languages are under-resourced 15 min
  2. Community efforts: building data and tools together 15 min
  3. Ethics of language data 15 min
  4. Quiz: 6 questions
Module 3: Designing a chatbot4 lessons

Plan goals, users, channels, intents, conversation flows, tone, languages and hand-off, and choose the right kind of bot.

  1. Goals, users and channels 15 min
  2. Intents, entities and conversation flows 20 min
  3. Fallback, human hand-off, tone and language 15 min
  4. Rule-based, retrieval and generative bots 20 min
  5. Quiz: 7 questions
Module 4: Building a chatbot3 lessons

Write a knowledge base and FAQ, build a bot with a free no-code tool, and try a short Python example.

  1. Writing a knowledge base and FAQ 20 min
  2. Building a no-code chatbot 25 min
  3. A beginner Python NLP example 25 min
  4. Quiz: 6 questions
Module 5: Testing, responsibility and the capstone3 lessons

Test with real users, measure success, protect privacy, make the bot accessible, and complete a bilingual FAQ chatbot capstone.

  1. Testing with real users and measuring success 20 min
  2. Privacy, consent and accessibility 20 min
  3. Capstone: a bilingual FAQ chatbot 25 min
  4. Quiz: 7 questions
Final exam

26 questions. Pass with 70% or more to earn your certificate.

What you need

  • Completed Practical AI Tools: Using AI Assistants Wisely (ai-tools-literacy), or equivalent experience with an AI chat assistant
  • A computer or smartphone with internet access
  • Basic Python (Introduction to Programming with Python) is helpful but not required

Further reading

More courses to explore

Intermediate 1 learner

Generative AI at Work: Prompting, Safety and Productivity

Use generative AI tools well and safely at work or school: write strong prompts, draft, summarise and analyse, check facts, protect private data, follow policy and build repeatable workflows.

What you will learn

  • How generative AI works
  • The art of prompting
  • AI for everyday work
  • 17 lessons
  • 5 h 35 min
  • Online, at your pace
View course

Advanced 1 learner

Introduction to Machine Learning

Learn how machines learn from data: prepare data, train and judge regression, tree, nearest-neighbour and clustering models with scikit-learn, avoid overfitting and bias, and finish a complete project.

What you will learn

  • What machine learning is and how to prepare for it
  • Predicting with simple models
  • Trees, forests and clusters
  • 17 lessons
  • 4 h 46 min
  • Online, at your pace
View course

To install on iPhone or iPad: tap the Share button in Safari, then choose "Add to Home Screen".