|
Title:
|
DETERMINISTIC TOURIST WALK FOR EFFECTIVE DIVERSIFICATION OF QUERY RESULTS |
|
Author(s):
|
Samuel Zanferdini Oliva, Joaquim Cezar Felipe and Marcela Xavier Ribeiro |
|
ISBN:
|
978-989-8533-95-1 |
|
Editors:
|
Hans Weghorn |
|
Year:
|
2019 |
|
Edition:
|
Single |
|
Keywords:
|
Information Retrieval, Query Processing, Retrieval Model and Ranking, Diversity |
|
Type:
|
Full Paper |
|
First Page:
|
163 |
|
Last Page:
|
170 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In this paper, we describe a new method for query results diversification, based on the deterministic tourist walk, that aims
to improve the semantics of the context. In this method, an initial candidate set produced by a query is used to construct a
result set, where objects are arranged regarding relevance and diversity features, for instance, the retrieved objects should
be as relevant as possible to the search object and, simultaneously, the result set should also be diversified. The major
contribution of this paper is that, through the new proposed method, which is an adaptation of the tourist walk, we
implement and evaluate a new way of performing the diversification of query results. We present an experimental
evaluation of the method comparing it to two well-known methods of diversifying queries. The experiments of the methods
were performed through the visualization of the data distribution on a metric map of two dimensions, however it is possible
to use more dimensions. Our experimental results demonstrated that the proposed method retrieves objects in a more
semantic way, regarding objects that are more scattered and better distributed throughout the dataset. |
|
|
|
|
|
|
