Scribd
Upload
15 views8 pages

Assigns Predefined Categories To Text Data AKA Text-Tagging Types

Text classification is a machine learning technique that assigns categories or tags to text data. There are different types of text classification including topic classification, sentiment analysis, and intent classification. The process involves pre-processing text, feature extraction, splitting data into training and test sets, building a classifier, predicting outcomes, and calculating accuracy. Topic modeling is an unsupervised machine learning technique that can scan documents, detect word patterns, automatically cluster related words and phrases, and help determine what topics users discuss.

Uploaded by

Chandrajeet Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
15 views8 pages

Assigns Predefined Categories To Text Data AKA Text-Tagging Types

Text classification is a machine learning technique that assigns categories or tags to text data. There are different types of text classification including topic classification, sentiment analysis, and intent classification. The process involves pre-processing text, feature extraction, splitting data into training and test sets, building a classifier, predicting outcomes, and calculating accuracy. Topic modeling is an unsupervised machine learning technique that can scan documents, detect word patterns, automatically cluster related words and phrases, and help determine what topics users discuss.

Uploaded by

Chandrajeet Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 8

• Assigns predefined categories to text data

• AKA Text-Tagging
• Types
• Topic Classification
• Sentiments Analysis
• Intent Classification
TEXT CLASSIFICATION

• Steps
• Pre-processing of text
• Feature Extraction from text
• Splitting the data into training and test
• Building the classifier
• Predicting the outcome and calculating accuracy
• Choosing the maximum accuracy
TEXT CLASSIFICATION
• Accuracy
TOPIC MODELLING

• Topic modeling is an unsupervised machine learning


technique that's capable of scanning a set of documents,
detecting word and phrase patterns within them, and
automatically clustering word groups and similar
expressions that best characterize a set of documents.

• With the help of topic modelling we aim at knowing what our


users are talking about and all that is relevant to them.
TOPIC MODELLING

• We pre-processed the data by removing the stop


words and passed it through word net lemmatizer.
• Before building the latent Dirichlet allocation model,
we have count vectorized our corpus and transformed
the data for further processing.
• We have prepared a document term matrix so that the
LDA model can look for the repeating term patterns in
the entire matrix to handle the text data.
TOPIC MODELLING

Removing Stop Words:


We iteratively add words which are not
relevant as stop words, and remove them from
our analyzer to get better results
TOPIC MODELLING

We performed topic modelling and got the


following results:
TOPIC MODELLING
• Topic 0: Topic 0 words are basically “Issues Encountered”. They talk about
the issues faced by the user while using the app .

• Topic 1: Topic 1 words speak about the “If it is worth it or not” of food
offered.

• Topic 2: Topic 2 words mostly talk about the “how and what users
purchased”
• Topic 3: Topic 3 talks about the “Characters of the protagonist”.
• Topic 4: Topic 5 words talk about the user experience.
With the help of the above, we can see what our users want and
associate ourselves accordingly with the need.

You might also like