01 Intro - Mind Map

Up: 01 Intro - Index

mindmap
  root((Text Mining))
    Basics
      90% unstructured
      Search vs discovery
      Applications
        Sentiment
        Info extraction
        Clustering
    Preprocessing
      Tokenization
      Stopwords
      Stemming
      Lemmatization
      POS tagging
    Features
      Bag of words
      TF-IDF
      Embeddings
    Feature selection
      Pruning
      POS filter
    Pattern discovery
      Clustering
        Jaccard
        Cosine
        Embedding sim
      Classification
        Naive Bayes
        SVM
        RNN LSTM
      Association
    Challenges
      Synonyms
      High dimensions
      Ambiguity

flowchart LR
    T[Text] --> P[Preprocessing]
    P --> F[Feature generation]
    F --> S[Feature selection]
    S --> D[Pattern discovery]
    D --> I[Interpretation]
    I -. feedback .-> T
    D --> CL[Clustering: Jaccard, cosine]
    D --> CF[Classification: sentiment]

Concepts: Concept - Text Mining, Concept - Text Mining Process, Concept - Bag of Words, Concept - TF-IDF, Concept - Word Embeddings, Concept - Pattern Discovery.