Topic modeling MCQs December 22, 2025November 19, 2024 by u930973931_answers 15 min Score: 0 Attempted: 0/15 Subscribe 1. What is Topic Modeling? (A) Summarizing the content of a document (B) Extracting named entities from text (C) Identifying underlying topics in a collection of documents (D) Converting text into numerical data 2. Which of the following is a common algorithm used in topic modeling? (A) K-means clustering (B) Decision Tree (C) Random Forest (D) Latent Dirichlet Allocation (LDA) 3. In LDA, what does the “Dirichlet distribution” represent? (A) Distribution of words across documents (B) Distribution of words within topics (C) Distribution of topics across documents (D) Distribution of the topic-per-word ratio 4. What does the output of topic modeling typically consist of? (A) Word clouds of frequent words (B) A set of topics with the distribution of words across them (C) Categorized list of documents (D) Ranked list of sentiment scores 5. What is the main goal of Topic Modeling? (A) Group documents into predefined categories (B) Extract topics and discover hidden thematic structures (C) Perform sentiment analysis (D) Generate word embeddings 6. Which of the following is a common application of topic modeling? (A) Organizing and summarizing large text collections (B) Generating captions for images (C) Detecting anomalies in data (D) Improving website search ranking 7. What is the key assumption made by LDA in topic modeling? (A) Each document is composed of a mixture of topics (B) Each topic contains a mixture of words (C) All of the above (D) The number of topics is known beforehand 8. In topic modeling, what does “topic coherence” refer to? (A) Degree to which words within a topic are related (B) Quality of topic labels (C) Distribution of topics across the dataset (D) Balance of topics within documents 9. Which of the following is a limitation of topic modeling techniques like LDA? (A) Requires large labeled datasets (B) Cannot handle stop words (C) Cannot handle numerical data (D) Often fails to capture subtle semantic relationships 10. How does the number of topics in LDA affect results? (A) More topics result in more granular topic discovery (B) Fewer topics cause overfitting (C) More topics lead to generalization (D) Number of topics has little impact 11. Which evaluation metric is often used to assess the quality of topics? (A) Accuracy (B) Precision (C) Recall (D) Topic coherence 12. What is “Topic Distribution” in topic modeling? (A) Probability of each word in a topic (B) Proportion of topics in a document (C) Set of topics generated from a corpus (D) Graph showing relationships between topics 13. Which is an example of a topic in a technology corpus? (A) cloud computing, data security, AI (B) sports, basketball, soccer (C) politics, elections, government (D) art, painting, sculpture 14. What is the main difference between Topic Modeling and Document Classification? (A) They are the same (B) Document classification finds topics, topic modeling classifies documents (C) Topic modeling is supervised, classification is unsupervised (D) Topic modeling is automatic, classification requires labeled data 15. What type of documents is topic modeling most useful for? (A) Fixed-structure documents like HTML pages (B) Large, unstructured text corpora (C) Images and videos (D) Structured data like spreadsheets