A special issue of International Journal of Metadata, Semantics and Ontologies
Nowadays, the Web is one of the dominant information sources for learning and acquiring new knowledge. However, finding the relevant information is still a huge challenge. To solve this problem, a significant research effort has been devoted to enhance linguistics and statistics based search by added semantics. In the recent years, many approached to semantic search have emerged. Ontologies are typically used by most of the approaches. Some approaches are relying on semantic annotations by adding additional metadata; some are enhancing clustering of retrieved documents according to topic or semantically enriching queries; some are developing powerful querying languages for ontology.
The progress and existing sparse evaluations of the semantic search tools offer a promising prospect to improve performance of traditional information retrieval (IR) systems. However, the results lack indications of whether this improvement is optimal, causing difficulties in benchmarking different semantic search systems. Yet, the majority of IR evaluation methods are mainly based on relevance of retrieved information, while additional sophistication of the semantic search tools adds complexity to user interaction to reach improved results. Therefore, standard IR metrics as recall and precision do not suffice alone to measure user satisfaction because of the complexity and efforts needed to use the semantic search systems. There is a need to investigate what ontology properties can further enhance search performance, to assess whether this improvement comes at a cost of interaction simplicity and user satisfaction, etc.
Furthermore, evaluation methods based on recall and precision do not indicate the causes for variation in different retrieval results. There are many other factors that influence the performance of ontology-based information retrieval, such as query quality, ontology quality, complexity of user interaction, difficulty of a searching topic with respect to retrieval, indexing, searching, and ranking methods. The detail analysis on how these factors and their interactions affect a retrieval process can help to dramatically improve retrieval methods or processes.
On the other hand, semantic search systems depend on correct information specified in ontology at the appropriate level of granularity and precision. An important body of work already exists in ontology quality assessment field. However, most of ontology evaluation methods are generic quality evaluation frameworks, which do not take into account application of ontology. Therefore there is a need for task- and scenario-based quality assessment methods that, in this particular case, would target and optimise ontology quality for use in information retrieval systems.
In order to promote more efficient and effective ontology usage in IR, there is a need to focus on analysis of ontology quality- and value-added aspects for this domain, summarise use cases and identify best practices. Several issues have been raised by the current research, such as the workload for annotation, the scalability, and the balance between the express power and reasoning capability. An approach to holistic evaluation should assess both technological and economical performance viewpoints. An aspect of value creation by semantics-based systems is important to demonstrate that the benefits of the new technology will overwhelm the payout.
The aim of this special issue is to present new and challenging issues in semantic search and how the solutions can be evaluated, compared and systemised. Therefore, submissions dealing with ontology quality aspects and their impact on IR results, evaluation of usability of the semantic search systems, analysis of user behaviour, new evaluation methods enabling thorough and fine-grained analysis of semantic search technological and/or financial performance, etc. are strongly encouraged.
Original and high quality submissions that focus on different evaluation aspects of semantic search are invited. The topics of interest include but are not limited to:
Evaluation of Semantic Search Systems :
- Evaluation of information retrieval efficiency and effectiveness
- Scalability assessment
- Assessment of annotation quality/labour-load
- Evaluation and benchmarking techniques and datasets
- Ontology quality evaluation
- Ontology utility in semantic search
- Ontology maintenance
- Query interpretation and refinement
- User acceptance of semantic technology
- Usability evaluation
- Interaction modes in semantic search
- Ratio of semantics processing cost/ retrieval utility
- Incentives for annotation and interaction
- Costs of maintenance of semantic search solutions
- Value of information
Submission of abstracts: May 17, 2009
Full paper submission: May 31, 2009
Notification about acceptance/rejection: August 15, 2009
Submission of revised version: September 27, 2009
Final camera-ready submission: November 15, 2009
No comments:
Post a Comment