Scribd
Upload
2 views9 pages

Sentiment Analysis

Uploaded by

simpleusesimpleuse
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views9 pages

Sentiment Analysis

Uploaded by

simpleusesimpleuse
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Sentiment Analysis

TEAM MEMBERS:
 C R.HEMANTH -1CE22AI010
 MOHAN.C C -1CE22AI035
 TEJAS.D P -1CE23AI402
DOMAIN
Topic : Sentiment Analysis in AI
Domain:
 Natural Language Processing (NLP).
 Artificial Intelligence (AI).
Focus:
 How sentiment analysis helps businesses understand customer
feedback, opinions, and competitor performance.
OBJECTIVE
 To review and analyze AI-based sentiment analysis techniques
used in competitive research.
 To explore the challenges faced in sentiment analysis.
 To highlight the advancements and methodologies improving
sentiment classification accuracy .
INTRODUCTION
 Sentiment analysis is used to identify and categorize opinions in
text data, often applied to product reviews and customer
feedback.
 AI-based sentiment analysis helps businesses gain insight into
customer sentiment and compare how their products are viewed
against competitors.
 Preprocessing is crucial for cleaning and preparing text for AI-
based models.
SOFTWARE USED
 Data-preprocessing using Python.
 Gemini Pro.
 ChatGPT API.
 AI Frameworks.
PROBLEM STATEMENT
 How to effectively analyze vast amounts of unstructured customer
feedback using sentiment analysis.
 Issues include handling spam, false data, domain dependency,
and negation in text.
 Understanding complex emotional cues from text is still a
challenge.
 Improving the accuracy and reliability of sentiment analysis for
competitive research purposes.
RESEARCH GAP
 Complex Emotions: Difficulty in detecting sarcasm, mixed, and
context-dependent emotions.
 Cultural Sensitivity: AI struggles with cultural context and idiomatic
expressions.
 Real-time Processing: Challenges in handling large-scale, real-
time text data.
 Multimodal Data: Limited integration of voice, images, and other
non-textual data for sentiment analysis.
 Spam Detection: Vulnerability to false data, bots, and fake
reviews.
LITERATURE SURVEY
 TITLE: Artificial Intelligence and Sentiment Analysis.
Author: Hamed Taherdoost and Mitra Madanchian.
 TITLE: Sentiment Analysis Methodologies, Practices And
Applications.
Author: Pooja Mehta and Dr.Sharnil Pandya.
 TITLE: A Survey on Sentiment Analysis.
Author: Mayur Wankhade and Chaitanya Kulkarni

You might also like