L15 - TF-IDF Approach

Question 1

1. What does TF-IDF stand for?

Answer 1

1. Term Frequency - Inverse Document Frequency

Question 2

2. How do we calculate the score if TF-IDF?

Answer 2

1. (Word counts of target text) / (word counts of other texts)

Question 3

3. What is the purpose of TF-IDF?

Answer 3

1. Establishes the important of terms in a document relative to a corpus of other documents

Question 4

4. Generally how does TF-IDF work?

Answer 4

1. Calculate the frequency of every term E.g corpus of metal lyrics
   
   2. For each document, calculate the TF-IDF score

Question 5

5. Explain the steps of the TF-IDP process…

Answer 5

1. Tokenise words i.e perform stemming or lemmatisation
   
   2. For each term in the document, calculate it’s frequency -> (Number of term occurrences) / (number of terms in document)
   3. Multiple TF and IDF values to get the TF-IDF score for each term
   4. Represent the TF-IDF scores in a document-term matrix