Semantic Search Interface Research Articles

A novel framework and concept-based semantic search Interface for abnormal crowd behaviour analysis in surveillance videos

Monitoring continuously captured surveillance videos is a challenging and time consuming task. To assist this issue, a new framework is introduced that applies anomaly detection, semantic annotation and provides a concept-based search interface. In particular, novel optical flow based features are used for abnormal crowd behaviour detection. Then, processed surveillance videos are annotated using a new semantic metadata model based on multimedia standards using Semantic Web technologies. In this way, globally inter-operable metadata about abnormal crowd behaviours are generated. Finally, for the first time, based on crowd behaviours, a novel concept-based semantic search interface is proposed. In the proposed interface, along with search results (video segments), statistical data about crowd behaviours are also presented. With extensive user studies, it is demonstrated that the proposed concept-based semantic search interface enables efficient search and analysis of abnormal crowd behaviours. Although there are existing works to achieve (a) crowd anomaly detection, (b) semantic annotation and (c) semantic search interface, none of the existing works combine these three system components in a novel framework like the one proposed in this paper. In each system component, we introduce contributions to the field as well as use the Semantic Web technologies to combine and standardize output of different system components; output of the anomaly detection is automatically annotated with metadata and stored to a semantic database. When continuous surveillance videos are processed, only the semantic database is updated. Finally, the user interface queries the updated database for searching/analyzing surveillance videos without changing any coding. Thus, the framework supports re-usability. This paper explains and evaluates different components of the framework.

SEAweb: the small RNA Expression Atlas web application.

We present the Small RNA Expression Atlas (SEAweb), a web application that allows for the interactive querying, visualization and analysis of known and novel small RNAs across 10 organisms. It contains sRNA and pathogen expression information for over 4200 published samples with standardized search terms and ontologies. In addition, SEAweb allows for the interactive visualization and re-analysis of 879 differential expression and 514 classification comparisons. SEAweb's user model enables sRNA researchers to compare and re-analyze user-specific and published datasets, highlighting common and distinct sRNA expression patterns. We provide evidence for SEAweb's fidelity by (i) generating a set of 591 tissue specific miRNAs across 29 tissues, (ii) finding known and novel bacterial and viral infections across diseases and (iii) determining a Parkinson's disease-specific blood biomarker signature using novel data. We believe that SEAweb's simple semantic search interface, the flexible interactive reports and the user model with rich analysis capabilities will enable researchers to better understand the potential function and diagnostic value of sRNAs or pathogens across tissues, diseases and organisms.

A framework for real-time semantic social media analysis

This paper presents a framework for collecting and analysing large volume social media content. The real-time analytics framework comprises semantic annotation, Linked Open Data, semantic search, and dynamic result aggregation components. In addition, exploratory search and sense-making are supported through information visualisation interfaces, such as co-occurrence matrices, term clouds, treemaps, and choropleths. There is also an interactive semantic search interface (Prospector), where users can save, refine, and analyse the results of semantic search queries over time. Practical use of the framework is exemplified through three case studies: a general scenario analysing tweets from UK politicians and the public’s response to them in the run up to the 2015 UK general election, an investigation of attitudes towards climate change expressed by these politicians and the public, via their engagement with environmental topics, and an analysis of public tweets leading up to the UK’s referendum on leaving the EU (Brexit) in 2016. The paper also presents a brief evaluation and discussion of some of the key text analysis components, which are specifically adapted to the domain and task, and demonstrate scalability and efficiency of our toolkit in the case studies.

A Framework for Real-Time Semantic Social Media Analysis

This paper presents a framework for collecting and analysing large volume social media content. The real-time analytics framework comprises semantic annotation, Linked Open Data, semantic search, and dynamic result aggregation components. In addition, exploratory search and sense-making are supported through information visualisation interfaces, such as co-occurrence matrices, term clouds, treemaps, and choropleths. There is also an interactive semantic search interface (Prospector), where users can save, refine, and analyse the results of semantic search queries over time. Practical use of the framework is exemplified through three case studies: a general scenario analysing tweets from UK politicians and the public’s response to them in the run up to the 2015 UK general election, an investigation of attitudes towards climate change expressed by these politicians and the public, via their engagement with environmental topics, and an analysis of public tweets leading up to the UK’s referendum on leaving the EU (Brexit) in 2016. The paper also presents a brief evaluation and discussion of some of the key text analysis components, which are specifically adapted to the domain and task, and demonstrate scalability and efficiency of our toolkit in the case studies.

Semantic Enrichment and Search: A Case Study on Environmental Science Literature

As information discovery needs become more and more challenging, traditional keyword-based information retrieval methods are increasingly falling short in providing adequate support. The problem is often compounded by the poor quality of article metadata in some digital collections. This paper investigates automatic semantic enrichment and search methods, as ways to meet these challenges. In particular, the benefits of enriching articles with knowledge from Linked Open Data resources are investigated, with focus on the domain of environmental science. In order to facilitate environmental science researchers in carrying out better semantic searches, a form-based semantic search interface is proposed. It helps researchers to benefit from the semantically enriched content, e.g. to carry out sophisticated location-based searches. The usability and ease of learning of this web interface were evaluated in a user-based study, the results of which are also reported.

Enabling entity retrieval by exploiting wikipedia as a semantic knowledge source

This dissertation research, PanAnthropon FilmWorld, aims to demonstrate direct retrieval of entities and related facts by exploiting Wikipedia as a semantic knowledge source, with the film domain as its proof-of-concept domain of application. To this end, a semantic knowledge base concerning the film domain has been constructed with the data extracted/derived from 10,640 Wikipedia pages on films and additional pages on film awards. The knowledge base currently contains 209,266 entities and 2,345,931 entity-centric facts. Both the knowledge base and the corresponding semantic search interface are based on the coherent classification of entities. Entity-centric facts are also consistently represented as <entity, attribute, value, note> tuples. The semantic search interface (http://dlib.ischool.drexel.edu:8080/sofia/PA/) supports multiple types of semantic search functions, which go beyond the traditional keyword-based search function, including the main General Entity Retrieval Query (GERQ) function, which is concerned with retrieving all entities that match the specified entity type, subtype, and semantic conditions and thus corresponds to the main research problem. Two types of evaluation have been performed in order to evaluate (1) the quality of information extraction and (2) the effectiveness of information retrieval using the semantic interface. The first type of evaluation has been performed by inspecting 11,495 film-centric facts concerning 100 films. The results have confirmed high data quality with 99.96% average precision and 99.84% average recall. The second type of evaluation has been performed by conducting an experiment with human subjects. The experiment involved having the subjects perform a retrieval task by using both the PanAnthropon interface and the Internet Movie Database (IMDb) interface and comparing their task performance between the two interfaces. The results have confirmed higher effectiveness of the PanAnthropon interface vs. the IMDb interface (83.11% vs. 40.78% average precision; 83.55% vs. 40.26% average recall). Moreover, the subjects' responses to the post-task questionnaire indicate that the subjects found the PanAnthropon interface to be highly usable and easily understandable as well as highly effective. The main contribution from this research therefore consists in achieving the set research goal, namely, demonstrating the utility and feasibility of semantics-based direct entity retrieval.