Week 10: Conclusion

This was the final week of my senior project! Throughout the week, I kept working on my Chrome extension and preparing for my final senior showcase presentation. Whilst meeting with my advisor to work on the extension, I have also been preparing for my presentation.

For this blog, I want to acknowledge all the people who helped me during my project. Firstly, special thanks to Mrs. Flood, my internal advisor, for being there for me every step of the way. Every meeting helped me stay on track and encouraged me to keep working hard on my project. Next, I would like to heartily thank my external advisor Dr. Akbari, for helping me throughout the entire process of my project. Each meeting was a lesson in CS, from working IDEs to TorchText functionality. I am grateful to have a great mentor who helped inspire me to continue pursuing ML. I would also like to thank Mrs. Bhattacharya for sitting through my practice presentation and giving me wonderful feedback. Lastly, I would like to acknowledge my friends Alison and Aashirya for giving me advice on my project from a student’s perspective. Thank you all!

On a different note, I would like to attach some of the most helpful and interesting resources I drew knowledge from. First, here are 5 of the top research papers that I read throughout my senior project. I would recommend giving them a read!

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0250419

https://arxiv.org/pdf/1705.01613.pdf

https://arxiv.org/pdf/2102.04458.pdf

https://www.researchgate.net/publication/369403094_Fake_News_Detection_using_Machine_Learning

https://scholarspace.manoa.hawaii.edu/server/api/core/bitstreams/60a92dd7-03cd-40b9-8f3e-a9d83f54efd2/content

Next, here are some links to some datasets that I could apply my model on, and depending on which one I decide to trial, training/testing may vary.

https://www.kaggle.com/datasets/hassanamin/textdb3

https://www.kaggle.com/datasets/mrisdal/fake-news

https://www.kaggle.com/datasets/mdepak/fakenewsnet

https://www.kaggle.com/datasets/techykajal/fakereal-news

https://www.kaggle.com/datasets/vikasg/russian-troll-tweets

https://www.kaggle.com/code/hamditarek/fake-news-detection-on-twitter-eda

Lastly, here are two miscellaneous links that I used extensively to either implement or learn from:

https://colah.github.io/posts/2015-08-Understanding-LSTMs/ (Understanding Neural Networks)

https://pytorch.org/text/0.10.0/_modules/torchtext/vocab.html (Pytorch’s TorchText.Vocab Source Code)

That concludes my senior project, thank you so much for experiencing this process with me!