Your Tribe Decides Your Vibe: Analyzing Local Popularity in the US Patent Citation Network

by   Nishit Narang, et al.
Association for Computing Machinery

In many networks, the indegree of a vertex is a measure of its popularity. Past research has studied indegree distributions treating the network as a whole. In the US Patent citation network (USPCN), patents are classified into categories and subcategories. A natural question arises: How do patents gather their popularity from various (sub)categories? We analyse local indegree distributions to answer this question. The citation (indegree) of a patent within the same category indicates its internal popularity, while a cross-category citation indicates its external popularity. We analyze the internal and external indegree distributions at each level of USPCN hierarchy to learn how the internal and external popularity of patents varies across (sub)categories. We find that all (sub)categories have local preferences that decide internal and external patents' popularities. Different patents are popular in different groups: Groups C1, C2 and C3 may not agree on popular patents in C1. In general, patent popularity appears to be a highly local phenomenon with subcategories (not even categories) deciding their own popular patents independent of the other (sub)categories.


Popularity Ranking of Database Management Systems

Databases are considered to be integral part of modern information syste...

Dynamic categories, dynamic operads: From deep learning to prediction markets

Natural organized systems adapt to internal and external pressures and t...

Viewing Computer Science through Citation Analysis; Salton and Bergmark Redux

Computer science has experienced dramatic growth and diversification ove...

A Study on Accuracy, Miscalibration, and Popularity Bias in Recommendations

Recent research has suggested different metrics to measure the inconsist...

Internal sums for synthetic fibered (∞,1)-categories

We give structural results about bifibrations of (internal) (∞,1)-catego...

Universality of citation distributions and its explanation

Universality or near-universality of citation distributions was found em...

Generating CCG Categories

Previous CCG supertaggers usually predict categories using multi-class c...

Please sign up or login with your details

Forgot password? Click here to reset