Modeling and Prediction

Develop predictive models using topic models and word embeddings

To find clusters and extract features from high-dimensional text datasets, you can use machine learning techniques and models such as LSA, LDA, and word embeddings. You can combine features created with Text Analytics Toolbox™ with features from other data sources. With these features, you can build machine learning models that take advantage of textual, numeric, and other types of data.

Functions

expand all

Word and N-Gram Counting

`bagOfWords`	Bag-of-words model
`bagOfNgrams`	Bag-of-n-grams model
`addDocument`	Add documents to bag-of-words or bag-of-n-grams model
`removeDocument`	Remove documents from bag-of-words or bag-of-n-grams model
`removeInfrequentWords`	Remove words with low counts from bag-of-words model
`removeInfrequentNgrams`	Remove infrequently seen n-grams from bag-of-n-grams model
`removeWords`	Remove selected words from documents or bag-of-words model
`removeNgrams`	Remove n-grams from bag-of-n-grams model
`removeEmptyDocuments`	Remove empty documents from tokenized document array, bag-of-words model, or bag-of-n-grams model
`topkwords`	Most important words in bag-of-words model or LDA topic
`topkngrams`	Most frequent n-grams
`encode`	Encode documents as matrix of word or n-gram counts
`tfidf`	Term Frequency–Inverse Document Frequency (tf-idf) matrix
`join`	Combine multiple bag-of-words or bag-of-n-grams models

Sentiment Analysis

`vaderSentimentScores`	Sentiment scores with VADER algorithm
`ratioSentimentScores`	Sentiment scores with ratio rule
`encode`	Tokenize and encode text for transformer neural network (Since R2023b)
`decode`	Convert token codes to tokens (Since R2023b)
`encodeTokens`	Convert tokens to token codes (Since R2023b)
`subwordTokenize`	Tokenize text into subwords using BERT tokenizer (Since R2023b)
`wordTokenize`	Tokenize text into words using tokenizer (Since R2023b)

Transformers

`bert`	Pretrained BERT model (Since R2023b)
`bertDocumentClassifier`	BERT document classifier (Since R2023b)
`classify`	Classify document using BERT document classifier (Since R2023b)
`bertTokenizer`	WordPiece BERT tokenizer (Since R2023b)
`bpeTokenizer`	Byte pair encoding tokenizer (Since R2024a)
`encode`	Tokenize and encode text for transformer neural network (Since R2023b)
`decode`	Convert token codes to tokens (Since R2023b)
`encodeTokens`	Convert tokens to token codes (Since R2023b)
`subwordTokenize`	Tokenize text into subwords using BERT tokenizer (Since R2023b)
`trainBERTDocumentClassifier`	Train BERT document classifier (Since R2023b)
`wordTokenize`	Tokenize text into words using tokenizer (Since R2023b)

Embeddings and Encodings

`documentEmbedding`	Document embedding model to map documents to vectors (Since R2024a)
`embed`	Map document to embedding vector (Since R2024a)
`fastTextWordEmbedding`	Pretrained fastText word embedding
`wordEncoding`	Word encoding model to map words to indices and back
`doc2sequence`	Convert documents to sequences for deep learning
`wordEmbeddingLayer`	Word embedding layer for deep learning neural network
`word2vec`	Map word to embedding vector
`word2ind`	Map word to encoding index
`vec2word`	Map embedding vector to word
`ind2word`	Map encoding index to word
`isVocabularyWord`	Test if word is member of word embedding or encoding
`readWordEmbedding`	Read word embedding from file
`trainWordEmbedding`	Train word embedding
`writeWordEmbedding`	Write word embedding file
`wordEmbedding`	Word embedding model to map words to vectors and back

Document Summarization and Similarity

`extractSummary`	Extract summary from documents (Since R2020a)
`rakeKeywords`	Extract keywords using RAKE (Since R2020b)
`textrankKeywords`	Extract keywords using TextRank (Since R2020b)
`bleuEvaluationScore`	Evaluate translation or summarization with BLEU similarity score (Since R2020a)
`rougeEvaluationScore`	Evaluate translation or summarization with ROUGE similarity score (Since R2020a)
`bm25Similarity`	Document similarities with BM25 algorithm (Since R2020a)
`cosineSimilarity`	Document similarities with cosine similarity (Since R2020a)
`textrankScores`	Document scoring with TextRank algorithm (Since R2020a)
`lexrankScores`	Document scoring with LexRank algorithm (Since R2020a)
`mmrScores`	Document scoring with Maximal Marginal Relevance (MMR) algorithm (Since R2020a)

Topic Modeling and Dimension Reduction

`fitlda`	Fit latent Dirichlet allocation (LDA) model
`fitlsa`	Fit LSA model
`resume`	Resume fitting LDA model
`logp`	Document log-probabilities and goodness of fit of LDA model
`predict`	Predict top LDA topics of documents
`transform`	Transform documents into lower-dimensional space
`ldaModel`	Latent Dirichlet allocation (LDA) model
`lsaModel`	Latent semantic analysis (LSA) model

Named Entity Recognition

`addEntityDetails`	Add entity tags to documents
`trainHMMEntityModel`	Train HMM-based model for named entity recognition (NER) (Since R2023a)
`predict`	Predict entities using named entity recognition (NER) model (Since R2023a)
`hmmEntityModel`	HMM-based model for named entity recognition (NER) (Since R2023a)

Visualization

`wordcloud`	Create word cloud chart from text, bag-of-words model, bag-of-n-grams model, or LDA model
`textscatter`	2-D scatter plot of text
`textscatter3`	3-D scatter plot of text

Topics

Classification and Modeling

Create Simple Preprocessing Function
This example shows how to create a function which cleans and preprocesses text data for analysis using the Preprocess Text Data Live Editor task.
Create Simple Text Model for Classification
This example shows how to train a simple text classifier on word frequency counts using a bag-of-words model.
Classify Documents Using Document Embeddings
This example shows how to train a document classifier by converting documents to feature vectors using a document embedding.
Analyze Text Data Using Multiword Phrases
This example shows how to analyze text using n-gram frequency counts.
Analyze Text Data Using Topic Models
This example shows how to use the Latent Dirichlet Allocation (LDA) topic model to analyze text data.
Choose Number of Topics for LDA Model
This example shows how to decide on a suitable number of topics for a latent Dirichlet allocation (LDA) model.
Compare LDA Solvers
This example shows how to compare latent Dirichlet allocation (LDA) solvers by comparing the goodness of fit and the time taken to fit the model.
Visualize Document Clusters Using LDA Model
This example shows how to visualize the clustering of documents using a Latent Dirichlet Allocation (LDA) topic model and a t-SNE plot.
Visualize LDA Topic Correlations
This example shows how to analyze correlations between topics in a Latent Dirichlet Allocation (LDA) topic model.
Visualize Correlations Between LDA Topics and Document Labels
This example shows how to fit a Latent Dirichlet Allocation (LDA) topic model and visualize correlations between the LDA topics and document labels.
Train Custom Named Entity Recognition Model
This example shows how to train a custom named entity recognition (NER) model.
Create Co-occurrence Network
This example shows how to create a co-occurrence network using a bag-of-words model.
Information Retrieval with Document Embeddings
Learn about different types of document embeddings and how to use them for information retrieval. (Since R2024b)
Information Retrieval with Work Orders Data
This example shows how to use information retrieval techniques to find solutions for new work orders based on past actions taken and descriptions from work orders. (Since R2023b)
Train BERT Document Classifier
This example shows how to train a BERT neural network for document classification. (Since R2023b)

Sentiment Analysis and Keyword Extraction

Sentiment Analysis in MATLAB
Learn about sentiment analysis techniques. (Since R2023b)
Analyze Sentiment in Text
This example shows how to use the Valence Aware Dictionary and sEntiment Reasoner (VADER) algorithm for sentiment analysis.
Generate Domain Specific Sentiment Lexicon
This example shows how to generate a lexicon for sentiment analysis using 10-K and 10-Q financial reports.
Train a Sentiment Classifier
This example shows how to train a classifier for sentiment analysis using an annotated list of positive and negative sentiment words and a pretrained word embedding.
Extract Keywords from Text Data Using RAKE
This example shows how to extract keywords from text data using Rapid Automatic Keyword Extraction (RAKE).
Extract Keywords from Text Data Using TextRank
This example shows to extract keywords from text data using TextRank.

Deep Learning

Classify Text Data Using Deep Learning
This example shows how to classify text data using a deep learning long short-term memory (LSTM) network.
Classify Text Data Using Convolutional Neural Network
This example shows how to classify text data using a convolutional neural network.
Classify Out-of-Memory Text Data Using Deep Learning
This example shows how to classify out-of-memory text data with a deep learning network using a transformed datastore.
Sequence-to-Sequence Translation Using Attention
This example shows how to convert decimal strings to Roman numerals using a recurrent sequence-to-sequence encoder-decoder model with attention.
Multilabel Text Classification Using Deep Learning
This example shows how to classify text data that has multiple independent labels.
Generate Text Using Deep Learning (Deep Learning Toolbox)
This example shows how to train a deep learning long short-term memory (LSTM) network to generate text.
Pride and Prejudice and MATLAB
This example shows how to train a deep learning LSTM network to generate text using character embeddings.
Word-by-Word Text Generation Using Deep Learning
This example shows how to train a deep learning LSTM network to generate text word-by-word.
Classify Text Data Using Custom Training Loop
This example shows how to classify text data using a deep learning bidirectional long short-term memory (BiLSTM) network with a custom training loop.
Generate Text Using Autoencoders
This example shows how to generate text data using autoencoders.
Define Text Encoder Model Function
This example shows how to define a text encoder model function.
Define Text Decoder Model Function
This example shows how to define a text decoder model function.
Language Translation Using Deep Learning
This example shows how to train a German to English language translator using a recurrent sequence-to-sequence encoder-decoder model with attention.
Extract Answers from Documents Using BERT
This example shows how to modify and fine-tune a pretrained BERT model for extractive question answering. (Since R2024b)
Out-of-Distribution Detection for BERT Document Classifier
Detect out-of-distribution (OOD) data in a BERT document classifier. (Since R2024b)
Out-of-Distribution Detection for LSTM Document Classifier
Detect out-of-distribution (OOD) data in an LSTM document classifier. (Since R2024a)

Language Support

Language Considerations
Information on using Text Analytics Toolbox features for other languages.
Japanese Language Support
Information on Japanese support in Text Analytics Toolbox.
Analyze Japanese Text Data
This example shows how to import, prepare, and analyze Japanese text data using a topic model.
German Language Support
Information on German support in Text Analytics Toolbox.
Analyze German Text Data
This example shows how to import, prepare, and analyze German text data using a topic model.

Featured Examples

Classify Text Data Using Deep Learning

Classify text data using a deep learning long short-term memory (LSTM) network.

Open Live Script

Analyze Text Data Using Multiword Phrases

Analyze text using n-gram frequency counts.

Open Live Script

Analyze Text Data Using Topic Models

Use the Latent Dirichlet Allocation (LDA) topic model to analyze text data.

Open Live Script