Paragrah$-1$

Affective computing is an interdisciplinary umbrella that comprises systems that recognize, interpret, process or simulate human feeling, emotion and mood. For example, some virtual assistants are programmed to speak conversationally or even to banter humorously; it makes them appear more sensitive to the emotional dynamics of human interaction, or to otherwise facilitate human$$computer interaction. However, this tends to give na$$ve users an unrealistic conception of how intelligent existing computer agents actually are. Moderate successes related to affective computing include textual sentiment analysis and, more recently, multimodal sentiment analysis, wherein AI classifies the affects displayed by a videotaped subject

Paragrah$-2$

The simplest AI applications can be divided into two types: classifiers $($e$.$g$."$if shiny then diamond"$),$ on one hand, and controllers $($e$.$g$."$if diamond then pick up$"),$ on the other hand. Classifiers are functions that use pattern matching to determine the closest match. They can be fine$-$tuned based on chosen examples using supervised learning. Each pattern $($also called an "observation"$)$ is labeled with a certain predefined class. All the observations combined with their class labels are known as a data set. When a new observation is received, that observation is classified based on previous experience.

Q$8$: Bayesian and conditional probability

a$.$ What is conditional probability? How Bayesian can be used for document classification? In

case of document classification how we can use semi$-$supervised learning?

b$.$ Take an example where Professor wants to cluster students based on their research paper to

determine the probability of one student copying answers of other student, or student using

generative tool to write answers. He wants to use Bayesian and K$-$means clustering for the

same. Write detailed approach and pseudo code. Then use semi$-$supervised learning for

grading.

c$.$ In 'paragraph$-1\text{'}$ and 'paragraph$-2\text{'}$ if each sentence is a separate document $-$ how can you

classify these sentences using semi$-$supervised learning.

d$.$ How can you represent these documents as graph using BoW approach? Write pseudo code

and work out the example for 'paragraph$-1\text{'}$ and 'paragraph$-2\text{'}.$

Q$9$: Context pointers and clustering

a$.$ What is meant by context pointers? Give an algorithm based on BoW to determine context

pointers. How can you derive context pointers $-$ in case of 'paragraph$-1\text{'}$ and 'paragraph$-2\text{'}.$

Use extractive summarization, word$-$based and phrase$-$based analysis for these two paragraphs

to derive context pointers. Write pseudo code.

b$.$ Assume that each sentence in these paragraphs are tweets. Then cluster these tweets using K$-$

means clustering. Use Manhattan and Euclidean distance separately for clustering. Then use an

approach to combine these two distance measures. Write pseudo code. Give worked out example.