# CSD501 / Data Science ## Syllabus {% file src="" %} {% file src="" %} ## Resources
M1: Introduction * Introduction to social media and natural language processing research * Collecting and extracting social media data using APIs
M2: Language Identification and Naïve Bayes * Domain and genre difference * Language identification * Supervised learning and classification * Naïve Bayes algorithm * Feature selection (Information Gain) * Text preprocessing * Tokenization * Emoticons handling * Noisy text normalization
M3: Overview of Paraphrase Research * Key resources and corpora * WordNet * DIRT * MRPC (Microsoft Research Paraphrase Corpus) * PPDB (Paraphrase Database) * Regression and classification models * Linear regression * Cost function * Gradient descent * Logistic regression * Decision boundary
M4: Vector Semantics * Unsupervised learning techniques * Class-based clustering * Brown clusters * Soft clustering * Singular Value Decomposition (SVD) * Neural word embeddings * Word2Vec * CBOW model * Skip-gram model
M5: Deep Learning for NLP * Neural network fundamentals * Neuron and activation function * Non-linearity and learning * Recurrent Neural Networks (RNNs) * Long Short-Term Memory (LSTM) networks * Advanced applications * Neural machine translation * Neural conversation generation * Sentiment analysis * Deep architectures and attention * Convolutional Neural Networks (CNNs) * Attention model
{% hint style="danger" %} Content Yet to be Updated for this Page, Submit Resources If you want to collaborate, find form attached on this page below. {% endhint %} ## Notes ### MidTerm ### EndSem \[⤓] ## Question Directory \[⤓] ### Assignment Questions \[⤓] ### Previous Year Questions #### Mid-Sem-PYQ
[⤓]Content Preview
Y3S5-CSD501-TSA-MidTerm-PYQ-OCT25
#### End-Sem-PYQ
[⤓]Content Preview
Y3S5-CSD501-TSA-EndSem-PYQ-JAN23
Y3S5-CSD501-TSA-EndSem-PYQ-DEC23
Y3S5-CSD501-TSA-EndSem-PYQ-DEC24
## External Sources \[⤓] *** {% embed url="" %} {% embed url="" %} {% embed url="" %}