Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn topic modeling and text classification techniques specifically designed for digital humanities applications through this comprehensive tutorial series that covers both fundamental concepts and practical implementation. Master the essential terminology and concepts including topics, clusters, bigrams, trigrams, and TF-IDF before progressing to hands-on implementation using industry-standard Python libraries. Explore rules-based topic modeling methods using TF-IDF with Scikit Learn, including data visualization with Matplotlib and K-Means clustering techniques. Dive into machine learning-based approaches through Latent Dirichlet Allocation (LDA) using Gensim, learning to create, optimize, and save topic models while handling bigrams, trigrams, and frequent word removal. Develop text classification skills using spaCy 3.x, focusing on dataset cultivation, training set generation with word vectors, and best practices for digital humanities research. Gain exposure to advanced libraries including TensorFlow and Keras, and discover modern approaches like Top2Vec for efficient topic modeling, all while building practical skills applicable to digital humanities research and text analysis projects.
