Scribd
Upload
8 views

DWM Exp 9

Experiment of datawarehousing

Uploaded by

cagona9497
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
8 views

DWM Exp 9

Experiment of datawarehousing

Uploaded by

cagona9497
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Experiment 09: Deployment of Fake News Detection

Group Members: -
TE COMP A-15 Nitya Bhave
TE COMP A-33 Jitesh Dubey
TE COMP A-58 Ameya Joshi

Introduction: In today's digital age, the rise of fake news poses a significant threat to reliable information
dissemination, leading to widespread misinformation. To combat this issue, we're conducting an experiment
to develop a Fake News Detection system using machine learning. By analyzing a dataset of fake and
genuine news articles, we'll train models to distinguish between factual and misleading information. Our
goal is to create a robust system that helps promote trustworthy journalism and safeguards against the spread
of false information in society.

Deployment:
 Data Collection:
Gather a comprehensive dataset containing both fake and genuine news articles. Ensure the dataset is
labeled accurately to distinguish between fake and genuine articles.

 Preprocessing:
Perform text preprocessing techniques such as tokenization, lowercasing, removal of stopwords, and
stemming. This step helps in standardizing the text data and reducing noise.

 Feature Engineering:
Utilize TF-IDF (Term Frequency-Inverse Document Frequency) to convert the preprocessed text data
into numerical features. TF-IDF reflects the importance of a word in a document relative to the entire
corpus.

 Model Training:
Train machine learning models, such as Support Vector Machine (SVM) and Random Forest, on the
training data. Employ hyperparameter tuning techniques like GridSearchCV to find the optimal model
parameters.

 Model Evaluation:
The Random Forest model is assessed using the test dataset, yielding an accuracy score and a
classification report. These metrics summarize the model's ability to classify news articles accurately
as fake or genuine.
 Deployment:
Deploy the Fake News Detection system for inference on new data. Ensure the deployed system is
robust and capable of handling real-world scenarios.

 Continuous Monitoring:
Continuously monitor the deployed system's performance and effectiveness. Update the models as
necessary to maintain accuracy and adapt to evolving fake news trends.

Conclusion: In conclusion, our experiment illustrates the powerful role of machine learning in detecting
fake news. Through meticulous training of models such as Support Vector Machine (SVM) and Random
Forest on a diverse dataset containing both fake and genuine news articles, we've successfully crafted a
robust Fake News Detection system. This system stands as a beacon of hope in the fight against
misinformation, bolstering the credibility of journalism in the digital age. Looking ahead, ongoing
monitoring and adaptation will be paramount to uphold its effectiveness amidst the ever-evolving landscape
of fake news.

For Faculty Use Only

Correction Formative Timely Attendance /


Parameters Assessment Completion of Learning Attitude
[40%] Practical [40%] [20%]
Marks
Obtaine
d

You might also like