Free-text Queries Research Articles

Detection and management of pornography-seeking in an online clinical dermatology atlas

Increased use of an online educational archive of photographic dermatology case materials (DermAtlas) indicated unexpected pornography-seeking behavior and misuse. We sought to assess the extent of archive misuse. Web usage/request patterns were examined over a 6-month period for requests by anatomic site, diagnosis, and age group plus anatomic site. Free-text queries and referrals from external Web sites were reviewed. Of 7800 images, 5.5% contain genital sites. Of all requests, 11% were for anatomic sites (37% genital sites); 62% were specified for diagnoses (12% genital sites). When age group and anatomic site were specified, the relative risk of a child being requested (vs adult) was 1.48 (95% confidence interval 1.44-1.53). Of 10000 free text queries, 12% retrieved images containing genital sites. Of all referrals, 14.3% originated from nonmedical (pornography/fetish) Web sites. Requests are mixed with legitimate queries. Online photographic dermatology archives are vulnerable to misuse. Monitoring and intervention are necessary to preserve their availability and integrity.

A knowledge-based approach for retrieving scenario-specific medical text documents

Medical free-text queries often share the same scenario. A scenario represents a repeating task in healthcare. For example, a specific scenario is searching for treatment methods for a specific disease, where “treatment” is a term indicating the scenario. To support scenario-specific retrieval, in this paper we present a new knowledge-based approach to address these problems. In addition, we describe a testbed system developed using the approach. Our specific implementation uses the UMLS Metathesaurus and semantic structure to extract key concepts from a free text. The approach uses phrase-based indexing to represent similar concepts, and query expansion to improve matching query terms with the terms in the document. The system formulates the query based on the user's input and the selected scenario template such as “disease, treatment” or “disease, diagnosis.” Thus, it is able to retrieve documents relevant to the specific scenario. Evaluating the system using the standard OSHMED corpus, our empirical results validate the effectiveness of this new approach over the traditional text retrieval techniques.

Comparisons Between Internet Users' Free-Text Queries and Controlled Vocabularies: A Case Study in Water Quality

ABSTRACT Free-text query terms were recorded from the University of Nebraska Water Quality Web Site. Comparisons were made between 3,275 free-text searches representing 2,075 unique terms and three controlled vocabularies: Library of Congress Subject Headings, Water Resources s Thesaurus, and Aqualine Thesaurus 2. Between 30 percent and 40 percent of the free-text queries were exact matches to a term in one of the controlled vocabularies. Other user query terms varied from the controlled vocabularies in whether the term was singular or plural, in spelling, and in word endings. About 40 percent of the terms had no near matches. Around 15 percent of the users included a non-subject resource descriptor. Resource descriptions of most interest to searchers were keywords, geographical delineators, and genre/format terms.

The eJBJS (www.jbjs.org)

The eJBJS (www.jbjs.org)

A video retrieval and sequencing system

Video is an effective medium for capturing the events in the real world around us, and a vast amount of video materials exists, covering a wide range of applications. However, widespread use of video in computer applications is often impeded by the lack of effective tools to manage video information systematically. This article discusses the design and implementation of a frame-based video retrieval and sequencing system (VRSS). The system is designed to support the entire process of video information management: segmenting, indexing, retrieving, and sequencing of video data. A semiautomatic tool is developed to divide video sequences into meaningful shots. Each video shot is logged using text descriptions, audio dialogue, and cinematic attributes. A two-layered, concept-based model is used as the basis for accurately retrieving relevant video shots based on users' free-text queries. A cinematic, rule-based, virtual editing tool is also developed to sequence the video shots retrieved for presentation within a specified time constraint. The system has been tested on a video documentary on the NUS (National University of Singapore) engineering faculty. The results of video retrieval experiments are encouraging.