Demystifying Legalese: An Automated Approach for Summarizing and Analyzing Overlaps in Privacy Policies and Terms of Service
Soneji, Shikha, Hoesing, Mitchell, Koujalgi, Sujay, Dodge, Jonathan
–arXiv.org Artificial Intelligence
This calls into question the reasonableness of expecting users to make informed decisions given that they do not comprehend the terms. A technology that can automate the simplification and categorization of popular ToS documents would be immensely beneficial, enhancing user understanding of accepted policies and facilitating the identification of concerning changes. We envision an automated system that begins with the text of a ToS document for a new product or service. The prospective user copies and pastes the text into an automated tool, which extracts key concepts and then presents some information in a format that is shorter and easier to read, such as a numeric/letter score alongside a bullet list of the most important concepts. Our work focuses on extracting key concepts from a data corpus we scraped from Terms of Service; Didn't Read (ToS;DR) [38].
arXiv.org Artificial Intelligence
Apr-17-2024
- Country:
- North America > United States
- Nevada (0.04)
- Pennsylvania > Centre County
- University Park (0.04)
- North America > United States
- Genre:
- Research Report (1.00)
- Industry:
- Law (1.00)
- Information Technology > Security & Privacy (1.00)
- Technology: