| Version | |
| Download | 15 |
| Total Views | 38 |
| Stock | ∞ |
| File Size | 232.67 KB |
| File Type |  |
| Create Date | August 25, 2018 |
| Last Updated | August 25, 2018 |
Personalized Search with Editable Profiles
Abstract—Personalized Search with Editable Profiles is an important technique for improving search performance. Existing approaches work in a black box, where users have no clue how it works and how to customize it. This lack of user control and flexibility can often be inconvenient and counter-productive. In this paper, we propose PEEPLER, a transparent search personalization framework that enables full user control and manipulation. In PEEPLER, a user can own multiple profiles and each can be modified arbitrarily. Profile terms can be automatically generated, manually entered, and expanded by adding their semantically related ones. In addition, negative terms are allowed for specification of negative preferences, which can be very useful in filtering undesirable results. The selected profile will help re-rank search results based on how consistent they are with respect to the profile. We implement PEEPLER in the context of Web search using Google Web search API, demonstrating the promise and potential of the approach.
Get IEEE 2018 Project Topics List