US 5,754,938 · Granted 1998-05-19

The 1998 Patent That Invented News Feed Personalization

Imagine a system that reads thousands of news articles and learns what you personally care about—then automatically ranks the articles most likely to interest you. This patent describes exactly that: software that builds a profile of your interests by analyzing word patterns, then matches you with content you'd actually want to read.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The claim covers a computerized system that automatically analyzes text documents (like news articles) by measuring how frequently each word appears relative to its overall use across all documents, then compares those 'target profiles' against a user's stored interest profile to rank-order which documents that user would find relevant. It also protects a cryptographic proxy server component that lets users keep their interest profiles private while still receiving personalized recommendations.

Why it matters

This patent captures the core mechanics of what became modern recommendation and content-filtering systems. Filed in 1995 and granted in 1998, it preceded the mainstream adoption of personalized news feeds and algorithmic ranking by several years. The inclusion of privacy protections through pseudonymous proxy servers also shows early awareness that personalization and privacy would be in tension—a debate that dominates tech policy today.

Real-world use

Every time you see a news app or social feed showing you stories ranked by relevance to your interests, or when Spotify suggests songs based on your listening history, you're encountering systems built on the principles this patent laid out.

Original USPTO abstract

This invention relates to customized electronic identification of desirable objects, such as news articles, in an electronic media environment, and in particular to a system that automatically constructs both a "target profile" for each target object in the electronic media based, for example, on the frequency with which each word appears in an article relative to its overall frequency of use in all articles, as well as a "target profile interest summary" for each user, which target profile interest summary describes the user's interest level in various types of target objects. The system then evaluates the target profiles against the users' target profile interest summaries to generate a user-customized rank ordered listing of target objects most likely to be of interest to each user so that the user can select from among these potentially relevant target objects, which were automatically selected by this system from the plethora of target objects that are profiled on the electronic media. Users' target profile interest summaries can be used to efficiently organize the distribution of information in a large scale system consisting of many users interconnected by means of a communication network. Additionally, a cryptographically-based pseudonym proxy server is provided to ensure the privacy of a user's target profile interest summary, by giving the user control over the ability of third parties to access this summary and to identify or contact the user.

Patent details

Publication number: US 5,754,938
Filing date: 1995-10-31
Grant date: 1998-05-19
Assignee: Herz; Frederick S. M. / Eisner; Jason M. / Salganicoff; Marcos
Inventor(s): HERZ; FREDERICK S. M., EISNER; JASON M., SALGANICOFF; MARCOS
CPC class: H04N21/44222

View original record on Google Patents →

Want to file your own patent?

If you're building any kind of recommendation or content-filtering system for consumer products, search our database to see what competitors have already locked down in your space.

Free patentability scan