Sources

Content sources

Backend

[1] Mentioned Academic Paper - “A_Practical_q-Gram_Index_for_Text_Retrieval_Allowing_Errors”: https://www.researchgate.net/publication/2747370_A_Practical_q-Gram_Index_for_Text_Retrieval_Allowing_Errors

Frontend

• Icons: All icons used are from Heroicons which are free to use under the MIT License. The only exception is the link icon next to the criticisms. That one I let ChatGPT generate because I couldn’t find one on Heroicons I liked.
• SentimentScore dynamic slider: This was generated with ChatGPT since I needed it to create a custom SVG.
• To create the intial design I used Figma.

Image sources

Backend

Image 1.1: Local screenshot Image 1.2: Local screenshot

Image 2.1: https://medium.com/@kuldeepkumawat195/hashing-in-python-sets-and-dictionaries-aa2fdbb3861f

Image 3.1: https://www.datacamp.com/blog/what-is-text-embedding-ai Image 3.2: https://medium.com/data-science/text-embeddings-comprehensive-guide-afd97fce8fb5 Image 3.3: https://businessanalytics.substack.com/p/cosine-similarity-explained Image 3.4: https://medium.com/geekculture/cosine-similarity-and-cosine-distance-48eed889a5c4 Image 3.5: Local Screenshot of graph generated with ~testing_scripts/visualize_embedding_models.py

Frontend

Image 4.1: Local Screenshot