Lefteris Kozanidis

Towards Faceted Search for Named Entity Queries

A considerable fraction of the web queries contain named entities. This, coupled with the fact that a proper name might refer to multiple entities, imposes the ever-increasing need that search engines handle efficiently named entity queries. In this paper, we present a technique that automatically identifies the distinct subject classes to which a named entity query might refer and selects a set of appropriate facets for denoting the query properties within every class. We also suggest a method that examines the distribution of the identified query facets within the contents of the query matching pages and groups search results according to their entity denotation types. Our preliminary study shows that our technique identifies useful facets for representing the named entity query properties in each of their referenced subject classes.

Adaptive Web Site Customization

In this paper, we propose a novel site customization model that relies on a topical ontology in order to learn the user interests as these are exemplified in their site navigations. Based on this knowledge, our mechanism personalizes the site’s content and structure so as to meet particular user needs. Experimental results demonstrate that our model has a significant potential in accurately identifying the user interests and show that site customizations that rely on the detected interests assist web users experience personalized navigations in the sites’ contents.

Keyword Identification within Greek URLs

In this paper we propose a method that identifies and extracts keywords within URLs, focusing on the Greek Web and especially on URLs containing Greek terms. Although there are previous works on how to process Greek online content, none of them focuses on keyword identification within URLs of the Greek web domain. In addition, there are many known techniques for web page categorization based on URLs but, none addresses the case of URLs containing transliterated Greek terms. The proposed method integrates two components; a URL tokenizer that segments URL tokens into meaningful words and a Latin–to–Greek script transliteration engine that relies on a dictionary and a set of orthographic and syntactic rules for converting Latin verbalized word tokens into Greek terms. The experimental evaluation of our method against a sample of 1,000 Greek URLs reveals that it can be fruitfully exploited towards automatic keyword identification within Greek URLs

Query selection for improved Greek web searches

As the Web becomes an integral part of our everyday life and the Internet-literate population grows rapidly, the Search Engine market is steadily gaining a high monetary value. Unfortunately, today, the distribution of the search market share is dominated by English-speaking users and stakeholders, basically because English is the lingua franca of the Web. Thus, although the majority of the Web users are non-English native speakers, they naturally gravitate to using English in order to explore the plentiful Web content. In this paper, we propose a query selection mechanism for assisting users perform successful non-English Web searches. Our mechanism combines linguistic analysis and Web mining techniques and aims at assisting users select informative and well-specified queries for expressing their information needs in languages other than English. Our technique is validated on a dataset of 70 Greek queries issued to Google search engine over a period of 3 weeks. Obtained results demonstrate that our query selection mechanism yields improved retrieval performance compared to existing non-English search strategies and as such we believe that it can be fruitfully deployed for other natural languages.

HiBO: mining web's favorites

HiBO is a bookmark management system that incorporates a number of Web mining techniques and offers new ways to search, browse, organize and share Web data. One of the most challenging features that HiBO incorporates is the automated hierarchical structuring of bookmarks that are shared across users. One way to go about organizing shared files is to use one of the existing collaborative filtering techniques, identify the common patterns in the user preferences and organize bookmarked files accordingly. However, collaborative filtering suffers from some intrinsic limitations, the most critical of which is the complexity of the collaborative filleting algorithms that inevitably leads to the latency in updating the user profiles. In this paper, we address the dynamic maintenance of personalized views to shared files from a bookmark management system perspective and we study ways of assisting Web users share their information space with the community. To evaluate the contribution of HiBO, we applied our Web mining techniques to manage a large pool of bookmarked pages that are shared across community members. Results demonstrate that HiBO has a significant potential in assisting users organize and manage their shared data across web-based social networks.