LDA (Latent Dirichlet Allocation)
Number of Topics (n_topics): The desired number of topics to be extracted from the corpus.
Document Topic Prior (alpha): The Dirichlet prior on the per-document topic distributions.
Topic Word Prior (beta): The Dirichlet prior on the per-topic word distribution.
Maximum Iterations (max_iter): The maximum number of iterations to run the algorithm.
NMF (Non-negative Matrix Factorization)
Number of Topics (n_components): The number of components or topics to find.
Initialization Method (init): Method used to initialize the procedure.
Solver (solver): The numerical solver to use.
Regularization Terms (alpha, l1_ratio): The regularization parameters.
LSA (Latent Semantic Analysis)
Number of Topics (n_components): The number of singular values and vectors to compute.
Algorithm (algorithm): The algorithm to use in computing the SVD.
Number of Iterations (n_iter): The number of iterations for randomized SVD solver.
pLSA (Probabilistic Latent Semantic Analysis)
Number of Topics (n_topics): The number of topics to model.
Maximum Iterations (max_iter): The maximum number of iterations for the algorithm.
Tolerance for Convergence (tol): The tolerance level for checking convergence.
HDP (Hierarchical Dirichlet Process)
Concentration Parameters (gamma, alpha): Parameters governing the distribution over the number of topics.
Initial Number of Topics (n_topics): The initial guess for the number of topics.
Total Number of Iterations (max_iter): The total number of iterations for inference.
CTM (Correlated Topic Model)
Number of Topics (num_topics): The number of topics in the model.
Variational Parameter for Correlation (nu): Parameter controlling the variational distribution of topic correlation.
Maximum Number of Iterations (max_iter): The maximum number of iterations to run the variational algorithm.
DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
Neighborhood Size (eps): The maximum distance between two samples for them to be considered as in the same neighborhood.
Min Points (min_samples): The number of samples in a neighborhood for a point to be considered as a core point.
Gibbs Sampling
Number of Topics (n_topics): The number of topics to sample.
Hyperparameters (alpha, beta): The hyperparameters for the Dirichlet prior distributions.
Number of Iterations (n_iter): The number of Gibbs sampling iterations.
Dirichlet Multinomial Mixture (DMM) Model
Number of Topics (n_topics): The number of topics to infer.
Dirichlet Concentration Parameter (alpha): The concentration parameter for the Dirichlet prior.
Maximum Number of Iterations (max_iter): The maximum number of iterations for the algorithm.
Biterm Topic Model (BTM)
Number of Topics (n_topics): The number of topics to find.
Dirichlet Priors (alpha, beta): The Dirichlet priors for topics and terms.
Number of Iterations (n_iter): The number of iterations for the algorithm.
Dynamic Topic Model (DTM)
Number of Topics (n_topics): The number of topics over time.
Hyperparameters for Topic Evolution (alpha, beta): The hyperparameters controlling the evolution of topics over time.
Number of Time Slices (time_slices): The number of time slices to divide the corpus into.
Anchor Words
Number of Topics (n_topics): The number of distinct topics to identify.
Sparsity Threshold (threshold): The threshold for considering an anchor word.
Labeled LDA
Number of Topics (n_topics): The number of topics correlated with labels.
Label Feature Strength (eta): The strength of label features.
Dirichlet Hyperparameters (alpha, beta): The hyperparameters for the Dirichlet prior.
Admixture Model
Number of Topics (n_topics): The number of topics to model.
Dirichlet Prior (alpha): The Dirichlet prior on the per-document topic distributions.
Sparse Additive Generative Model (SAGE)
Number of Topics (n_topics): The number of topics to model.
Sparsity Regularizations (l1, l2): The regularization terms for sparsity.
Neural Topic Model
Number of Topics (n_topics): The number of topics to be modeled by the neural network.
Architecture Parameters (number of layers, number of neurons): The parameters defining the neural network architecture.
Learning Rate (learning_rate): The rate at which the model learns during training.
Regularization Terms: Parameters to prevent overfitting.
Guided LDA
Number of Topics (n_topics): The number of topics to guide the model towards.
Seed Topic List: A list of seed words for the topics.
Dirichlet Hyperparameters (alpha, eta): The Dirichlet hyperparameters for topic-word distributions.
Wondershare EdrawMind
