Browse Prior Art Database

Identifying social trend currents

IP.com Disclosure Number: IPCOM000228163D
Publication Date: 2013-Jun-10
Document File: 1 page(s) / 23K

Publishing Venue

The IP.com Prior Art Database

Abstract

When accessing information, users are sometimes oblivious to trends that have changed over time. Such users would likely be interested to know that the trend has changed so that they can adjust to the new situation and remain updated. We propose an apparatus to detect shifting in trends that could be implemented and used in a real world application.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 57% of the total text.

Page 01 of 1

Identifying social trend currents

When accessing information, users are sometimes oblivious to trends that have changed over time. For instance, a user searching for the keyword "Java"* may be unaware that people that use to search for Java* in the past now tend to search more for alternative programming languages. Another example, that would be very relevant a few years ago, is of someone using a particular social network then. Such a user would likely be interested to know that the trend has changed towards using a newer social network today instead. This type of scenario is also applicable when purchasing items. For instance, someone interested in purchasing a server, may be interested to know that people that use to purchase servers in the past, tend to purchase a cloud service instead nowadays. Another example is a change in research topic trends. For instance,

research on relational databases declined and is being replaced by research on non-relational databases.

    The issue of trend detection has gained a lot of attention in recent years and different formal approaches have been studied (see [1, 2, 3] below). This line of work, however, does not deal with detecting shifts in trends, namely that a specific trend was replaced by a new one over time. To achieve this task, a new approach must be adopted.

    Another related area is "users who searched/bought X also searched for/bought Y". This line of research is termed collaborative filtering and exists as a featu...