A Personalized Graph-Based Document Ranking Model Using a Semantic User Profile

Author(s):  
Mariam Daoud ◽  
Lynda Tamine ◽  
Mohand Boughanem
2011 ◽  
Vol 37 (6) ◽  
pp. 614-636 ◽  
Author(s):  
Mariam Daoud ◽  
Lynda Tamine ◽  
Mohand Boughanem

The goal of search personalization is to tailor search results to individual users by taking into account their profiles, which include their particular interests and preferences. As these latter are multiple and change over time, personalization becomes effective when the search process takes into account the current user interest. This article presents a search personalization approach that models a semantic user profile and focuses on a personalized document ranking model based on an extended graph-based distance measure. Documents and user profiles are both represented by graphs of concepts issued from predefined web ontology, namely, the Open Directory Project directory (ODP). Personalization is then based on reordering the search results of related queries according to a graph-based document ranking model. This former is based on using a graph-based distance measure combining the minimum common supergraph and the maximum common subgraph between the document and the user profile graphs. We extend this measure in order to take into account a semantic recovery at exact and approximate concept-level matching. Experimental results show the effectiveness of our personalized graph-based ranking model compared with Yahoo and different personalized ranking models performed using classical graph-based measures or vector-space similarity measures.


Information ◽  
2019 ◽  
Vol 10 (2) ◽  
pp. 39
Author(s):  
Zhenyang Li ◽  
Guangluan Xu ◽  
Xiao Liang ◽  
Feng Li ◽  
Lei Wang ◽  
...  

In recent years, entity-based ranking models have led to exciting breakthroughs in the research of information retrieval. Compared with traditional retrieval models, entity-based representation enables a better understanding of queries and documents. However, the existing entity-based models neglect the importance of entities in a document. This paper attempts to explore the effects of the importance of entities in a document. Specifically, the dataset analysis is conducted which verifies the correlation between the importance of entities in a document and document ranking. Then, this paper enhances two entity-based models—toy model and Explicit Semantic Ranking model (ESR)—by considering the importance of entities. In contrast to the existing models, the enhanced models assign the weights of entities according to their importance. Experimental results show that the enhanced toy model and ESR can outperform the two baselines by as much as 4.57% and 2.74% on NDCG@20 respectively, and further experiments reveal that the strength of the enhanced models is more evident on long queries and the queries where ESR fails, confirming the effectiveness of taking the importance of entities into account.


2019 ◽  
Vol 20 (1) ◽  
pp. 176-201
Author(s):  
ZEYNEP GOKCE CAKIR ◽  
GULIZ BILGIN ALTINOZ ◽  
BURCU H OZUDURU

2021 ◽  
pp. 1-23
Author(s):  
Shashank Kumar ◽  
Jeevitha Shree DV ◽  
Pradipta Biswas

BACKGROUND: Web accessibility is one of the most important aspects of building a website. It is important for web developers to ensure that their website is accessible according to WCAG standards for people with different range of abilities. There is plethora of tools for ensuring conformance to WCAG standards but not many studies compared performance of automatic WCAG tools. OBJECTIVE: This paper compares a set of ten WCAG tools and their results in terms of ease of comprehension and interpretation by web developers. We proposed a Common User Profile format to help personalize contents of website making it accessible to people with different range of abilities. METHODS: We selected ten WCAG tools from World Wide Web Consortium (W3C) to evaluate landing pages of two popular websites. For each webpage, we identified accessibility issues and recommended alternate suggestions to help developers improve accessibility. Further, we highlighted accessibility issues that cannot be captured only through conformance to WCAG tools; and proposed additional methods to evaluate accessibility through an Inclusive User Model. We then demonstrated how simulation of user interaction can capture usability and accessibility issues that are not detected through only syntactic analysis of websites’ content. Finally, we proposed a Common User Profile format that can be used to compare and contrast accessibility systems and services, and to simulate and personalize interaction for users with different range of abilities. RESULTS AND CONCLUSIONS: After careful evaluation of two websites using the ten tools, we noted that, both websites lacked color contrast between background and foreground; lack of sign language alternatives; opening of pop-ups without proper warnings and so on. Further, results from comparative analysis of selected web accessibility tools noted that, there is no single tool that can be found ideal in all aspects. However, from our study, Utilitia Validator by Utilitia SP. z O.O was considered the most feasible tool. By rectifying and incorporating issues and alternate suggestions by simulation study and Common User Profile format respectively, developers can improve both websites making it accessible to maximum audience.


Sign in / Sign up

Export Citation Format

Share Document