• Simranjeet kaur

Fake news detection and their analysis is a rapidly growing field of research due to the explosive growth in social media and internet. In artificial intelligence-based modern world, the detection of news reliability is one of the essential tools to extract textual information from massive news data. To the best of our knowledge, the exiting fake news detection system not able to detect the reliability of news with maximum accuracy and need a big improvement. So, in this research article, we designed an Improved Fake News Detection (I-FND) system using the concept of optimized Term Frequency-Inverted Document Frequency (TF-IDF) features with Multi-Level Voting Rule as machine learning technique. To select the best feature set from the extracted TF-IDF features, the concept of Swarm-based Grasshopper Optimization (SGO) technique is used as an optimization algorithm with a novel fitness function. The proposed I-FND system used four steps named as the pre-processing for data normalization, feature extraction using TF-IDF extractor, feature optimization or selection using SGO and classification with multi-level voting as concept of machine learning. The proposed I-FND system outperformed compare to the existing works and to validate the performance of the proposed work parameters such as accuracy, error, precision, recall, f-measure and execution time are computed. Based on the comparison, we founded that the proposed model work effectively in terms of performance parameters and we achieved noteworthy increase in accuracy, precision, recall and f-measure of proposed I-FND system

Fake News, Textual data, TF-IDF Feature Extraction, SGO, Multi-level voting, Machine learning

"An Improved Fake News Detection System using optimized TF-IDF Features with Multi Level Voting Rule", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.g5-g15, June-2021, Available :http://www.jetir.org/papers/JETIR2106828.pdf

"An Improved Fake News Detection System using optimized TF-IDF Features with Multi Level Voting Rule", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppg5-g15, June-2021, Available at : http://www.jetir.org/papers/JETIR2106828.pdf