Twine serviced
information storage, authoring and discovery through its website and browser-based tools. The service, intended for regular web users, attempted to automate certain processes related to data categorization and
keyword-association (tagging). The system employed
natural language processing and
machine learning to
extract concepts from written text in user data, The extracted data could be used in searches to additionally select the type of thing the user wanted to find, such as
person or
location. Twine was a
social network and its users could add contacts, send private messages and share information. Users could collaborate on collecting data through private or public
twines; data collections focused on a certain topic, such as politics. Data could be imported to Twine's website through conventional uploading of files, writing text with a
WYSIWYG editor or using a
bookmarking tool for
webpages. The tool worked similarly to other
social bookmarking websites. Users could manually write summaries, specify keywords (tags) and select an image to include in the bookmark that appears on Twine's website. Certain types of media in bookmarks, such as
YouTube videos, were automatically embedded in Twine's pages when bookmarked. Twine also offered limited
wiki capabilities to collaboratively edit documents. Information discovery was mostly done through a user's main page where items appeared, organized by the twine they belonged to. Twine also used
machine learning technologies that used semantic
metadata to learn and generate more relevant, automatic information recommendations of possible interest to the user. == History ==