Search Solutions 2019 - Tutorials
Search Solutions is the BCS Information Retrieval specialist group's annual event focused on practitioner issues in the arena of search and information retrieval.
The tutorials take place on Monday 26 November one day before the Search Solutions.
The tutorials offer conference attendees and local participants a stimulating and informative selection of practical training courses reflecting current topics and state-of-the-art methods in search and information retrieval. These tutorials will be presented by subject matter experts and will reflect the high academic and professional standards of the Search Solutions conference series.
We offer scholarships or fee waivers for unemployed BCS members looking to advance their careers: please contact the tutorial chair (firstname.lastname@example.org) if you are eligible and interested.
Morning Session 09:30 - 13:00
Tutorial 1 - Search Recommendations in a Marketplace, Instructor: Rishabh Mehrotra, Spotify
Multi-sided marketplaces are steadily emerging as viable business models in many applications (e.g. Amazon, AirBnb, YouTube), where in the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer). Such market places involve interaction between multiple stakeholders among which there are different individuals with assorted needs. While traditional search & recommender systems focused specifically towards increasing consumer satisfaction by providing relevant content to the consumers, multi-sided market places face an interesting problem of optimizing their models for supplier preferences, and visibility. In this tutorial, we consider a number of research problems which need to be addressed when developing a search & recommendation framework powering a multi-stakeholder market place.
We begin by contrasting traditional search & recommendations systems with those needed for marketplaces, and identify four key research areas which need to be addressed. First, we highlight the importance of a multi-objective ranking/recommendation module which jointly optimizes the different objectives of stakeholders while serving recommendations. Second, we discuss different ways in which stakeholders specify their objectives, and highlight key issues faced when quantifying such objectives. Third, we discuss user specific characteristics (e.g. user receptivity) which could be leveraged while jointly optimizing business metrics with user satisfaction metrics. Furthermore, we highlight important research questions to be addressed around evaluation of such systems, specifically focusing on quantifying user dissatisfaction and trade-off analysis between objectives. Finally, we end the tutorial by discussing a number of real world case-studies of such multi-stakeholder search and recommendation systems, and highlight recent findings.
Tutorial 2 - Reliability and Validity of Systematic Searches, Instructor: Farhad Shokraneh, University of Nottingham
Researchers were using questionnaires for decades to collect the data. To make sure that the questionnaires fit the purpose and can be repeated, validating them and checking their reliability became part of the questionnaire design process. Systematic reviews are using search methods for collecting the relevant literature. Despite considerable differences between designing a questionnaire and developing a search strategy, some principles of designing the questionnaire including validity and reliability are generalisable to designing the search. Search methods have also shown adoptability of concepts such are sensitivity and specificity that are being used in diagnostic test accuracy.
This tutorial discusses a multi-disciplinary approach in designing and evaluating the search strategies and filters discussing the differences among the disciplines. The tutorial will discuss types of validity including face validity, construct validity, criterion validity, formative validity, sampling validity, and known-group validity in context of designing search strategy. Furthermore, the tutorial will be inclusive of content on test-retest reliability, parallel-form reliability, inter-rater reliability, and internal consistency reliability. We will discuss how these concepts could help the design of better search strategies for systematic searching noting that some of these concepts are already being used in development of search filters.
Afternoon Session 14:00 - 17:30
Tutorial 3 - Text Analysis with GATE, Instructor: Diana Maynard, University of Sheffield
This tutorial takes a detailed view of key text mining tasks (introduction to NLP, linguistic pre-processing, entity and relation recognition, semantic annotation, indexing and multi-paradigm search) of textual content. It will cover both the latest state-of-the-art research and selected established methods and tools. It will show how text analysis tools and techniques can be used to assist with semantic search by providing extra information that is not explicit within the text itself. Finally, some real-world applications of the technology will be demonstrated, showcasing the entire pipeline of data collection, annotation, indexing, search and visualization.
Tutorial 4 - Reproducible and Replicable Search for Research Methods in Systematic Reviews, Instructors: Farhad Shokraneh, University of Nottingham
Although the systematic reviews are considered as the highest levels of research evidence in decision making process; however, the quality of such reviews depend on the reliability and strength of the search and research methods. Systematic search methods unlike the other research methods are not standard and the number of search results for the same research question is different from one searcher to another. To make the search methods reliable, here, we will present three solutions: 1. using evidence-based search methods; 2. recording and reporting the repeatable search methods; and 3: sharing the search results as part of the research results and test collection. To comply with open data initiative, we will present the methods to share the search reports and results without breaking the copyright law.
Tutorial 5 - Designing Search, Tony Russell-Rose, UXLabs and Goldsmiths, University of London
Search is not just a box and ten blue links. Search is a journey: an exploration where what we encounter along the way changes what we seek. But in order to guide people along this journey, we must understand both the art and science of user experience design. The aim of this tutorial is to deliver a learning experience grounded in good scholarship, integrating the latest research findings with insights derived from the practical experience of designing and optimizing dozens of commercial search applications. It focuses on the development of transferable, practical skills that can be learnt and practiced within a half-day session.
BCS, The Chartered Institute for IT
25 Copthall Avenue
Registration fees (including VAT at 20%) are as follows (per tutorial):
Early Bird Rates (until 23:59 on 31 Oct 2019)
BCS/ISKO member rate: £90
Non-member rate: £110
Normal Rates (from 1 Nov 2019 until 23:59 on 22 Nov 2019)
BCS/ISKO member rate: £110
Non-member rate: £130
Registration is now open on Eventbrite
Closing date for bookings is Friday 22 November 2019 at 12:00 noon. No more bookings will be taken after this date.
Cancellations & Refunds
Full refund available if cancellation received before 12:00 noon on Friday 22nd November 2019. Name substitutions will be allowed if notified before the closing date.
For overseas delegates who wish to attend the event please note that BCS does not issue invitation letters.
Dr A. MacFarlane, City University London (Chair)
Dr. F. Hopfgartner, University of Sheffield
Dr. H. Liu, University of Bedfordshire