Sentiment analysis
Explore how models estimate the sentiment expressed in text
ExploreTurn language data into understanding
Learn how text becomes model input. Explore tokenization, sentiment analysis, conversational systems and language models with practical explanations for developers in Canada.
Our working method
The principles behind our educational resources
Careful review
Concepts are explained with attention to assumptions and practical limits
Clear explanations
Complex ideas explained in clear, direct language
Resources that keep evolving
Our resources follow the changing tools and ideas behind NLP
Practical context
Examples connect the underlying ideas to development decisions
Featured resources
Starting points for learning NLP
Tokenization: turning text into useful units
See how text is split into tokens, where different methods behave differently and why the choice affects the rest of your pipeline.
Read the full guideWhy learn natural language processing?
Understand the language technologies behind everyday applications
A widely used skill
Language technologies appear in search, support and document tools. Understanding their foundations helps developers in Canada evaluate which approach suits a particular task.
Build a foundation
Start with the relationship between text, tokens and predictions. Our guides introduce the concepts in stages, without assuming a background in linguistics.
Practical applications
Connect the fundamentals to tasks such as sorting feedback, retrieving information and building conversational interfaces. Consider failure cases alongside possible uses.
Ready to explore?
Choose a topic, work through the explanation and identify a small experiment you can try in your own project.
Get in touchCommon questions
Do I need previous NLP experience?
The guides introduce core concepts for developers new to NLP. Familiarity with basic programming will help you work through technical examples.
Which programming languages do you cover?
The concepts apply across languages such as Python, JavaScript and Java. Some examples use Python because of its established NLP ecosystem.
Where should I begin?
Start with tokenization to understand how text becomes model input. Then explore sentiment analysis or chatbot architecture according to your interests.
Are there code examples?
The resources connect concepts to practical examples. Where an example includes code, check its dependencies and adapt it to your own environment before use.
Our learning approach
How we explain and share NLP concepts
Research beyond the headline
We draw on technical documentation and research to explain both the method and the conditions under which it is useful.
Clear writing
We explain technical ideas in accessible language while keeping the details that affect development decisions.
Practical examples
Examples illustrate development decisions and trade-offs. Test any implementation against your own data and requirements.
Reader feedback
Reader questions help us improve explanations and revisit topics as the field changes.
We use local storage to remember your privacy choice. Read our cookie policy for details.