0% found this document useful (0 votes)
1 views12 pages

Sentiment Analysis of Social Media Post Using NLP

Sentiment analysis is a computational technique used to determine the emotional tone of social media posts, helping businesses improve products and customer relationships. It employs natural language processing (NLP) techniques for data preprocessing and utilizes models like RNN, AvgNet, and CNN for analysis. Challenges include sarcasm and informal language, but the insights gained are valuable for businesses, political analysts, and researchers.

Uploaded by

jaswanthkanjula
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
0% found this document useful (0 votes)
1 views12 pages

Sentiment Analysis of Social Media Post Using NLP

Sentiment analysis is a computational technique used to determine the emotional tone of social media posts, helping businesses improve products and customer relationships. It employs natural language processing (NLP) techniques for data preprocessing and utilizes models like RNN, AvgNet, and CNN for analysis. Challenges include sarcasm and informal language, but the insights gained are valuable for businesses, political analysts, and researchers.

Uploaded by

jaswanthkanjula
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/ 12

Sentiment Analysis Of Social Media

Post Using Nlp


Introduction to Sentiment Analysis

Sentiment analysis is a computational


technique used to determine the
emotional tone behind a series of
words.

It is widely applied to social media


posts to gauge public opinion on
various topics.

Understanding sentiment can help


businesses improve their products and
customer relationships.
Basics of Natural Language Processing (NLP)

NLP is a field of artificial intelligence


the interaction between computers
and human language.

Techniques in NLP enable machines to


read, understand, and derive meaning
from text.

The integration of NLP into sentiment


analysis enhances the accuracy of
emotional assessments.
Preprocessing Data

1. Text Cleaning: Remove URLs, mentions, special characters, and


convert text to lowercase for consistency.

2. Tokenization: Split text into individual words or phrases for easier


analysis.

3. Noise Removal: Remove stopwords, replace emojis with text, and


process hashtags for meaningful sentiment cues.

4. Normalization: Use lemmatization or stemming to reduce words to


their base form and expand slang/abbreviations.

5. Vectorization: Convert text into numerical format using methods like


TF-IDF, Word2Vec, or embeddings for model input.
NLP Models Used:-

For sentiment analysis modeling, we have employed three deep NLP based models, as
follows:
1.Recurrent Neural Network (RNN) Based (aka The Baseline)
2.Your Average Sentiment Network (aka AvgNet)
3.Convolutional Neural Network (CNN) Based (aka CNet)
Next, we briefly explain these three models and their training and evaluation details.

1. Recurrent Neural Network (RNN) Based (aka The Baseline)


This is the first NLP based model for sentiment analysis task. It consists of Recurrent Neural
Network (RNN) based nodes with learnable parameters. First, each word is vectorized using a
dictionary vector, followed by passing through the 100-D per word embedding layer. Then, we
have RNN nodes, outputting hidden state (next layer input). Finally, the last hidden state output
passes through the fully connected (FC) layer to yield the sentiment result.
2. Your Average Sentiment Network (aka AvgNet)
This model works similar to the above, except it uses Global Average Pooling insted
of RNN nodes.

3. Convolutional Neural Network (CNN) Based (aka CNet)


This model uses convolutional neural network (CNN) absed approach instead of
conventional NLP/RNN method. But still very effective as shown in the evaluation and
performance section later.
Results:-
Challenges in Sentiment Analysis

Sarcasm and irony can complicate


sentiment detection in social media
posts.

The informal nature of social media


language, including slang and
abbreviations, poses additional
challenges.

Variability in user expression can lead


to inconsistencies in sentiment
classification.
Real-World Applications

Businesses use sentiment analysis to


monitor brand reputation and
customer satisfaction.

Political analysts leverage sentiment


analysis to gauge public opinion
during elections.

Researchers apply sentiment analysis


to study social phenomena and trends
over time.
Conclusion

Sentiment analysis of social media


posts provides valuable insights for
businesses and researchers alike.

The combination of NLP techniques


and social media data offers a
powerful tool for understanding public
sentiment.

Continued advancements in
technology will further enhance the
capabilities and applications of
sentiment analysis.
THANK YOU

You might also like