Utilising information foraging theory for user interaction with image query auto-completion
Affiliation
University of BedfordshireIssue Date
2020-03-17Subjects
information foragingQuery Auto Completion
interactive information retrieval
Information Foraging Theory
information retrieval
G500 Information Systems
Metadata
Show full item recordOther Titles
Proceedings European Conference on Information Retrieval (ECIR 2020)Abstract
Query Auto-completion (QAC) is a prominently used feature in search engines, where user interaction with such explicit feature is facilitated by the possible automatic suggestion of queries based on a prefix typed by the user. Existing QAC models have pursued a little on user interaction and cannot capture a user’s information need (IN) context. In this work, we devise a new task of QAC applied on an image for estimating patch (one of the key components of Information Foraging Theory) probabilities for query suggestion. Our work supports query completion by extending a user query prefix (one or two characters) to a complete query utilising a foraging-based probabilistic patch selection model. We present iBERT, to fine-tune the BERT (Bidirectional Encoder Representations from Transformers) model, which leverages combined textual-image queries for a solution to image QAC by computing probabilities of a large set of image patches. The reflected patch probabilities are used for selection while being agnostic to changing information need or contextual mechanisms. Experimental results show that query auto-completion using both natural language queries and images is more effective than using only language-level queries. Also, our fine-tuned iBERT model allows to efficiently rank patches in the image.Citation
Jaiswal AK, Liu H, Frommholz I (2020) 'Utilising information foraging theory for user interaction with image query auto-completion', European Conference on Information Retrieval - Lisbon, Springer.Publisher
SpringerAdditional Links
https://www.springerprofessional.de/en/utilising-information-foraging-theory-for-user-interaction-with-/17887616https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148231/
Type
Conference papers, meetings and proceedingsLanguage
enISBN
9783030454388Sponsors
QUARTZae974a485f413a2113503eed53cd6c53
10.1007/978-3-030-45439-5_44
Scopus Count
Collections
The following license files are associated with this item:
- Creative Commons
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc-nd/4.0/
Related items
Showing items related by title, author, creator and subject.
-
An examination of information systems and technology maturity and it’s relationship to methods of contributing information to the information systems planning process in National Health Service acute trust hospitalsMitchell, Ivan John (University of Bedfordshire, 1996-05)As a result of the use of Nolan's six Stage model of IS and IT maturity in a number of consultancy studies in the early 1980s, managers felt they could maximise the contribution of the IS and IT portfolios to the achievement of business strategy by becoming more IS and IT mature. Despite the development of a further eight models since 1979, empirical tests exist only of the Nolan model and one other, McFarlan, McKenney and Pyburn's model ofIT assimilation. This research has sought further empirical evidence of IS and IT maturity in National Health Service (NHS) acute Trust hospitals. Survey method was used to collect data from over seventy top and middle managers representing four Trust hospitals. Statistical analysis of these data provided evidence that six of twenty-three maturity characteristics identified in existing models can currently be used to differentiate the maturity of NHS acute Trust hospitals. These six characteristics had been identified both in models which considered a range of IS and IT issues and in models which had concentrated on a single aspect of IS and IT management. This indicated that further insight is gained by combining these approaches when modelling IS and IT maturity. Managers also placed different emphasis on the use of specific methods of contributing information to the IS planning process in hospitals which exhibited greater IS and IT maturity than in hospitals which exhibited lesser IS and IT maturity. This indicates the existence ,of a further IS maturity characteristic, further evidence of which can now be sought in other industry sectors.
-
Applying Cross-cultural theory to understand users’ preferences on interactive information retrieval platform designChessum, Karen; Liu, Haiming; Frommholz, Ingo; University of Bedfordshire (University of Nottingham, School of Computer Science., 2014-09)In this paper we look at using culture to group users and model the users’ preference on cross cultural information retrieval, in order to investigate the relationship between the user search preferences and the user’s cultural background. Initially we review and discuss briefly website localisation. We continue by examining culture and Hofstede’s cultural dimensions. We identified a link between Hofstede’s five dimensions and user experience. We did an analogy for each of the five dimensions and developed six hypotheses from the analogies. These hypotheses were then tested by means of a user study. Whilst the key findings from the study suggest cross cultural theory can be used to model user’s preferences for information retrieval, further work still needs to be done on how cultural dimensions can be applied to inform the search interface design.
-
Development and evaluation of a brine mining equipment monitoring and control system using wireless sensor network and fuzzy logicHe, Liu; Cui, Yan; Duan, Yanqing; Stankovski, Stevan; Zhang, Xiaoshuan; Zhang, Jian; China Agricultural University; University of Bedfordshire; University of Novi sad; Beijing Information Science & Technology University (SAGE, 2017-03-29)The brine mining equipment failure can seriously affect the productivity of the salt lake chemical industry. Traditional monitoring and controlling method mainly depends on manned patrol that is offline and ineffective. With the rapid advancement of information and communication technologies, it is possible to develop more efficient online systems that can automatically monitor and control the mining equipment and to prevent equipment damage from mechanical failure and unexpected interruptions with severe consequences. This paper describes a Wireless Monitoring and feedback fuzzy logic-based Control System (WMCS) for monitoring and controlling the brine well mining equipment. Based on the field investigations and requirement analysis, the WMCS is designed as a Wireless Sensors Network module, a feedback fuzzy logic controller, and a remote communication module together with database platform. The system was deployed in existing brine wells at demonstration area without any physical modification. The system test and evaluation results show that WMCS enables to track equipment performance and collect real-time data from the spot, provides decision support to help workers overhaul the equipment and follows the deployment of fuzzy control in conjunction with remote data logging. It proved that WMCS acts as a tool to improve management efficiency for mining equipment and underground brine resources.