Using MATLAB for Sentiment Analysis and Text Analytics

Using MATLAB for Sentiment Analysis and Text Analytics

By Liliana Medina

MathWorks UK ¨C Software Engineer

MATLAB Text Analytics Toolbox

? 2018 The MathWorks, Inc.

1

Outline

?

?

?

?

Sentiment Analysis

Strings in MATLAB

Introduction to Text Analytics Toolbox

Using the toolbox for a sentiment analysis task

¨C Overview

¨C Step-by-step

¨C Insights

?

Additional capabilities and Resources

2

Sentiment Analysis

? Identify sentiment expressed in documents and social media

?

Microblogging platforms, news articles, company reports, e-mails

Applications

? Volatility and Risk analytics

? Inform trading strategies

? Correlate with stock movements

? Economics research

? Litigation

3

Strings

The better way to work with text

?

Manipulate, compare, and store text data efficiently?

>> "image" + (1:3) + ".png"

1¡Á3 string array

"image1.png"

?

"image2.png"

"image3.png"

Simplified text manipulation functions

¨C Example: Check if a string is contained within another string

? Previously:

if ~isempty(strfind(textdata,"Dog"))

?

?

Now:

if contains(textdata,"Dog")

Performance improvement

¨C Up to 50x faster using contains with string than strfind with cellstr

¨C Up to 2x memory savings using string over cellstr

4

Text Analytics Toolbox

Extract Value from Text Data

Statistics & Machine

Learning Toolbox

Model and Derive Insights

Preprocess Data

Access and Explore Data

Cleanup Text

RT @wsv Dry, warm

and sunny for most

today.#weatherRepor

t

Convert to Numeric

cat

dog

run

two

doc1

1

0

1

0

doc2

1

1

0

1

Dry warm sunny today

?

?

?

?

?

Word Docs

PDF¡¯s

Text Files

HTML

Tables/Spreadsheets

?

?

?

?

Stop Words

Stemming

Tokenization

Find special tokens

?

?

?

?

Bag of Words

Bag of N-grams

TF-IDF

Word Embeddings

?

?

?

?

Latent Dirichlet Allocation (LDA)

Latent Semantic Analysis (LSA)

Word clouds

Text scatter plots

Neural Network

Toolbox

5

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download