NLP Basics: Understanding Bag of Words and TF-IDF
AI Learning Project
NLP Basics: Understanding Bag of Words and TF-IDF
An introduction to the most fundamental text representation methods in NLP: Bag of Words (BoW) and TF-IDF.
AI Learning Project

NLP Basics: Understanding Bag of Words and TF-IDF

Reading info

Level: Beginner Reading time: 8 min
  • NLP
  • Bag of Words
  • TF-IDF
  • Machine Learning
Open knowledge map

After learning about image-based deep learning, the next most common field to explore is Natural Language Processing (NLP). Unlike images, which are fixed grids of pixels, text is a sequence of characters of varying length. Machines cannot read words directly. This brings us to the first core challenge in NLP: how do we convert words into numbers that a computer can process?

This article serves as an introduction to NLP. We will look at two of the most traditional and classic text representation methods: the Bag of Words (BoW) model and TF-IDF. Although they are simple, they remain highly effective for many basic classification tasks.

1. The Most Intuitive Approach: Bag of Words

Imagine a bag filled with words. When you receive a sentence, you only care about which words appear in it and how many times they appear, completely ignoring word order and grammatical structure.

The specific steps are very straightforward:

  1. Build a Vocabulary: Collect all the unique words that appear across all texts and put them in a fixed order. For example: ["AI", "is", "fun", "learning", "hard"].
  2. Count Frequencies: For any new sentence, count how many times each word in the vocabulary appears.

For example, if we remove words outside the vocabulary, the frequency vector for the sentence “learning AI is fun and learning is hard” might look like this:

# Vocabulary: ["AI", "is", "fun", "learning", "hard"]
# Vector:     [1, 2, 1, 2, 1]

In this way, a piece of text of arbitrary length is converted into a fixed-length numerical vector. It can then be fed into logistic regression or a neural network for classification.

2. Limitations of Bag of Words

Bag of Words is simple and intuitive, but it has several obvious flaws:

  • Extremely Sparse Vectors: In real applications, a vocabulary might contain tens of thousands to hundreds of thousands of words, while a single sentence typically contains only a few dozen. The vast majority of positions in the generated vector will be 0, causing serious memory and computation waste.
  • Ignores Semantic Relationships: “Good” and “excellent” mean roughly the same thing, but in the BoW model, they are two completely orthogonal dimensions with no connection whatsoever.
  • Complete Loss of Order: “Dog bites man” and “Man bites dog” have exactly the same BoW representation, but their meanings in reality are entirely different.

3. Improving Word Frequency: TF-IDF

In the BoW model, common words like “the,” “is,” and “a” will appear frequently in almost every document. If we only look at word frequency, the algorithm might mistakenly think these words are the most important. TF-IDF was designed to solve this problem.

TF-IDF stands for Term Frequency – Inverse Document Frequency. It considers not only how frequently a word appears in the current document (TF) but also how rare it is across all documents (IDF).

An intuitive understanding of the formula:

  • TF (Term Frequency): The number of times the word appears in this specific document. The more frequent, the more it represents the document’s topic.
  • IDF (Inverse Document Frequency): log(Total Documents / Documents containing the word). If a word is present in almost all documents, its IDF approaches 0, reducing its weight.

TF-IDF aggressively downweights words like “the” while amplifying the importance of rare but key terms like “machine” or “quantum”. It is excellent for keyword extraction or simple text classification.

4. A Stepping Stone to Deep Learning

Whether using the Bag of Words model or TF-IDF, they essentially rely on statistical features of words. The model doesn’t truly understand the meaning of the words; it only remembers the probabilities of which words tend to appear together.

Due to the curse of dimensionality, the lack of sequence information, and the inability to comprehend semantics, these classic methods fall short in complex tasks like dialogue understanding or machine translation. To overcome these shortcomings, the NLP field introduced concepts like “Word Embeddings” and “Recurrent Neural Networks (RNNs),” which will be the focus of our next article.

Internal links

Related tutorials

Review foundation Machine Learning Workflow

Follow the practical path from data and features to training, prediction, and evaluation.

 Continue next RNN Basics: Handling Sequential Data with Memory

Understand the core concepts of Recurrent Neural Networks (RNN), the role of hidden states, and their application in NLP.

 Topic hub Student AI Projects

Connect handwritten digits, browser demos, and CNN projects into a portfolio path.

 Knowledge map Knowledge Map

See how this article connects to projects, resources, and learning routes.

Search questions

FAQ

Who is this article for?

This article is for readers who want a beginner-level guide to NLP Basics: Understanding Bag of Words and TF-IDF. It takes about 8 min and focuses on NLP, Bag of Words, TF-IDF, Machine Learning.

What should I read next?

The recommended next step is RNN Basics: Handling Sequential Data with Memory, so the article connects into a longer learning route instead of ending as an isolated note.

Does this article include runnable code or companion resources?

This article is primarily explanatory, but the related tutorials point to runnable examples, resources, and project pages.

How does this article fit into the larger site?

It is connected to the article context block, learning routes, resources, and project timeline so readers can move from concept to implementation.

Article context

AI Learning Project

A practical route from AI concepts to machine learning workflow, evaluation, neural networks, Python practice, handwritten digits, a CIFAR-10 CNN, adversarial traffic-defense notes, and AI security.

Level: Beginner Reading time: 8 min
  • NLP
  • Bag of Words
  • TF-IDF
  • Machine Learning

Your next step

Continue: RNN Basics: Handling Sequential Data with Memory
View project
Other language version 人工智能 NLP 基础：词袋模型与 TF-IDF 详解
Share summary NLP Basics: Understanding Bag of Words and TF-IDF

An introduction to the most fundamental text representation methods in NLP: Bag of Words (BoW) and TF-IDF.

Open share center

Leave a Reply

Project timeline

Published posts

  1. AI Basics Learning Roadmap Separate AI, machine learning, and deep learning before going into implementation details.
  2. Machine Learning Workflow Follow the practical path from data and features to training, prediction, and evaluation.
  3. Model Training and Evaluation Understand loss, overfitting, train/test splits, accuracy, recall, and F1.
  4. Neural Network Basics Move from perceptrons to activation, forward propagation, backpropagation, and training loops.
  5. NLP Basics: Understanding Bag of Words and TF-IDF An introduction to the most fundamental text representation methods in NLP: Bag of Words (BoW) and TF-IDF.
  6. RNN Basics: Handling Sequential Data with Memory Understand the core concepts of Recurrent Neural Networks (RNN), the role of hidden states, and their application in NLP.
  7. Transformer Self-Attention Read Q/K/V, scaled dot-product attention, multi-head attention, and positional encoding before exploring LLM internals.
  8. Python AI Mini Practice Run a small scikit-learn classification task and read the experiment output.
  9. Handwritten Digit Dataset Basics Read train.csv, test.csv, labels, and the flattened 28 by 28 pixel layout before training the classifier.
  10. Handwritten Digit Softmax in C Follow the C implementation from logits and softmax probabilities to confusion matrices and submission export.
  11. Handwritten Digit Playground Notes See how the offline classifier was adapted into a browser demo with drawing input and probability output.
  12. CIFAR-10 Tiny CNN Tutorial in C Build and train a small convolutional neural network for CIFAR-10 image classification, then read its loss and accuracy output.
  13. Building a Tiny CIFAR-10 CNN in C: Convolution, Pooling, and Backpropagation A source-based walkthrough of cifar10_tiny_cnn.c, covering CIFAR-10 binary input, 3x3 convolution, ReLU, max pooling, fully connected logits, softmax, backpropagation, and local commands.
  14. High-Entropy Traffic Defense Notes Study encrypted metadata leaks, entropy, traffic classifiers, and a defensive Python chaffing prototype.
  15. AI Security Threat Modeling Build a defense map with NIST adversarial ML, MITRE ATLAS, and OWASP LLM risks.
  16. Adversarial Examples and Robust Evaluation Evaluate clean and perturbed accuracy with an FGSM-style digits experiment.
  17. Data Poisoning and Backdoor Defense Study poison rate, trigger behavior, attack success rate, and training pipeline controls.
  18. Model Privacy and Extraction Defense Measure membership inference signal and surrogate fidelity against a local toy model.
  19. LLM, RAG, and Agent Security Separate instructions from data and enforce tool permissions against indirect prompt injection.

Published resources

  1. Python AI practice code guide The article includes a runnable scikit-learn classification script.
  2. digit_softmax_classifier.c The C source for the handwritten digit softmax classifier.
  3. train.csv.zip Compressed handwritten digit training set with 42000 labeled samples.
  4. test.csv.zip Compressed handwritten digit test set with 28000 unlabeled samples.
  5. sample_submission.csv The official submission format example for checking the final output columns.
  6. submission.csv The prediction file generated by the current C project.
  7. digit-playground-model.json The compact softmax demo model and sample set used by the browser playground.
  8. digit-sample-grid.svg A small handwritten digit preview grid extracted from the training set.
  9. Handwritten digit project bundle Contains the source file, compressed datasets, submission files, browser model, and preview grid.
  10. cifar10_tiny_cnn.c source Single-file C tiny CNN with CIFAR-10 loading, convolution, pooling, softmax, and backpropagation.
  11. model_weights.bin sample weights Model weights generated by one local small-sample run.
  12. test_predictions.csv sample predictions Sample test prediction output from the CIFAR-10 tiny CNN.
  13. CNN project explanation PDF Companion explanation material for the CNN project.
  14. Virtual Mirror redacted code skeleton A redacted mld_chaffing_v2.py control-flow skeleton with secrets, node topology, and target lists removed.
  15. Virtual Mirror stress-test template A redacted CSV template for CPU, memory, peak threads, pulse rate, latency, and error measurements.
  16. Virtual Mirror classifier-evaluation template A CSV template for TP, FN, FP, TN, accuracy, precision, recall, F1, ROC-AUC, entropy, and JS divergence.
  17. Virtual Mirror resource notes Notes explaining why the public resources include only redacted code, test templates, and architecture context.
  18. AI Security Lab README Setup, safety boundaries, and quick-run commands for the AI Security series.
  19. AI Security Lab full bundle Includes safe toy scripts, result CSVs, risk register, attack-defense matrix, and architecture diagram.
  20. AI security risk register CSV risk register template for AI threat modeling and release review.
  21. AI attack-defense matrix Maps attack surface, toy demo, metric, and defensive control into one CSV table.
  22. AI Security Lab architecture diagram Shows threat modeling, robustness, data integrity, model privacy, and RAG guardrails.
  23. FGSM digits robustness script FGSM-style perturbation and accuracy-drop experiment for a local digits classifier.
  24. Data poisoning and backdoor toy script Demonstrates poison rate, trigger behavior, and attack success rate on digits.
  25. Model privacy and extraction toy script Outputs membership AUC, target accuracy, surrogate fidelity, and surrogate accuracy.
  26. RAG prompt injection guard toy script Uses a deterministic toy agent to demonstrate external-data demotion and tool-policy blocking.
  27. Deep Learning topic share card A 1200x630 SVG card for sharing the Deep Learning / CNN topic hub.
  28. Machine Learning From Scratch share card A 1200x630 SVG card for the K-means, Iris, and ML workflow topic hub.
  29. Student AI Projects share card A 1200x630 SVG card for handwritten digits, C classifiers, and browser demos.
  30. CNN convolution scan animation An 8-second Remotion animation showing how a 3x3 convolution kernel scans an input and builds a feature map.

Current route

  1. AI Basics Learning Roadmap Learning path step
  2. Machine Learning Workflow Learning path step
  3. Model Training and Evaluation Learning path step
  4. Neural Network Basics Learning path step
  5. Transformer Self-Attention Learning path step
  6. LLM Visualizer Learning path step
  7. Python AI Mini Practice Learning path step
  8. Handwritten Digit Dataset Basics Learning path step
  9. Handwritten Digit Softmax in C Learning path step
  10. Handwritten Digit Playground Notes Learning path step
  11. CIFAR-10 Tiny CNN Tutorial in C Learning path step
  12. High-Entropy Traffic Defense Notes Learning path step
  13. AI Security Threat Modeling Learning path step
  14. Adversarial Examples and Robust Evaluation Learning path step
  15. Data Poisoning and Backdoor Defense Learning path step
  16. Model Privacy and Extraction Defense Learning path step
  17. LLM, RAG, and Agent Security Learning path step

Next notes

  1. Add more image-classification and error-analysis cases
  2. Turn common metrics into a quick reference
  3. Add more AI security defense experiment notes