Natural Language Processing: Text Mining and Analytics Proficiency (Advanced Level)

  • 17m
  • 17 questions
The Text Mining and Analytics Proficiency (Advanced Level) benchmark measures your working experience with natural language processing (NLP) techniques and tools, such as text mining and analytics, spaCy, NLTK, NLP libraries, and sentiment analysis. Learners who score high on this benchmark demonstrate that they have good working experience in text mining and analytics using natural language processing and can work on NLP text analytics projects independently without any supervision.

Topics covered

  • build and evaluate simple NLP models
  • compare challenges and deployment strategies for NLP projects across various industries
  • demonstrate additional features of TextBlob including sentiment analysis, classification models, tokenization, word/phrase frequencies, word inflection, and spelling correction
  • demonstrate advanced Genism features such as identifying query similarity
  • demonstrate building an LDA model for topic modeling using genism
  • demonstrate building bigram and trigram for topic modeling using Genism
  • demonstrate feature engineering on data
  • demonstrate installation and topic modeling with Gensim
  • demonstrate multi-language part of speech tagging and morphological analysis using PolyGlot
  • demonstrate multi-language parts of speech tagging using polyglot including language detection, sentiment analysis, and transliteration
  • demonstrate simple model building and evaluation using the Decision Tree classifier, logistic regression, and SVM
  • demonstrate simple model building and evaluation using the Random Forest Classifier, Naïve Bayes, and KNN and compare the results of all the models
  • demonstrate the use of a word cloud and sentiment distribution
  • deploy AutoML, PyCaret, and Streamlit models
  • identify best practices for NLP projects across various industries
  • install linguistic features including noun phrase extraction, POS, parsing, and WordNet integration
  • interpret the tuning of models for better results and outline their evaluation using different search methods