Susan Craw

AAAI Conference 2018 Conference Paper

An E-Learning Recommender That Helps Learners Find the Right Materials

• Blessing Mbipom
• Stewart Massie
• Susan Craw

Learning materials are increasingly available on the Web making them an excellent source of information for building e-Learning recommendation systems. However, learners often have difficulty finding the right materials to support their learning goals because they lack sufficient domain knowledge to craft effective queries that convey what they wish to learn. The unfamiliar vocabulary often used by domain experts creates a semantic gap between learners and experts, and also makes it difficult to map a learner’s query to relevant learning materials. We build an e-Learning recommender system that uses background knowledge extracted from a collection of teaching materials and encyclopedia sources to support the refinement of learners’ queries. Our approach allows us to bridge the gap between learners and teaching experts. We evaluate our method using a collection of realistic learner queries and a dataset of Machine Learning and Data Mining documents. Evaluation results show our method to outperform benchmark approaches and demonstrates its effectiveness in assisting learners to find the right materials.

IJCAI Conference 2018 Conference Paper

Maintenance of Case Bases: Current Algorithms after Fifty Years

• Jose M. Juarez
• Susan Craw
• J. Ricardo Lopez-Delgado
• Manuel Campos

Case-Based Reasoning (CBR) learns new knowledge from data and so can cope with changing environments. CBR is very different from model-based systems since it can learn incrementally as new data is available, storing new cases in its case-base. This means that it can benefit from readily available new data, but also case-base maintenance (CBM) is essential to manage the cases, deleting and compacting the case-base. In the 50th anniversary of CNN (considered the first CBM algorithm), new CBM methods are proposed to deal with the new requirements of Big Data scenarios. In this paper, we present an accessible historic perspective of CBM and we classify and analyse the most recent approaches to deal with these requirements.

AIJ Journal 2015 Journal Article

Learning pseudo-tags to augment sparse tagging in hybrid music recommender systems

• Ben Horsburgh
• Susan Craw
• Stewart Massie

Online recommender systems are an important tool that people use to find new music. To generate recommendations, many systems rely on tag representations of music. Such systems, however, suffer from tag sparsity, whereby tracks lack a strong tag representation. Current state-of-the-art techniques that reduce this sparsity problem create hybrid systems using multiple representations, for example both content and tags. In this paper we present a novel hybrid representation that augments sparse tag representations without introducing content directly. Our hybrid representation integrates pseudo-tags learned from content into the tag representation of a track, and a dynamic weighting scheme limits the number of pseudo-tags that are allowed to contribute. Experiments demonstrate that this method allows tags to remain dominant when they provide a strong representation, and pseudo-tags to take over when tags are sparse. We show that our approach significantly improves recommendation quality not only for queries with a sparse tag representation but also those that are well-tagged. Our hybrid approach has potential to be extended to other music representations that are used for recommendation but suffer from data sparsity, such as user profiles.

IJCAI Conference 2015 Conference Paper

Music Recommenders: User Evaluation Without Real Users?

• Susan Craw
• Ben Horsburgh
• Stewart Massie

Good music recommenders should not only suggest quality recommendations, but should also allow users to discover new/niche music. User studies capture explicit feedback on recommendation quality and novelty, but can be expensive, and may have difficulty replicating realistic scenarios. Lack of effective offline evaluation methods restricts progress in music recommendation research. The challenge is finding suitable measures to score recommendation quality, and in particular avoiding popularity bias, whereby the quality is not recognised when the track is not well known. This paper presents a low cost method that leverages available social media data and shows it to be effective. Not only is it based on explicit feedback from many users, but it also overcomes the popularity bias that disadvantages new/niche music. Experiments show that its findings are consistent with those from an online study with real users. In comparisons with other offline measures, the social media score is shown to be a more reliable proxy for opinions of real users. Its impact on music recommendation is its ability to recognise recommenders that enable discovery, as well as suggest quality recommendations.

AAAI Conference 2012 Conference Paper

Music-Inspired Texture Representation

• Ben Horsburgh
• Susan Craw
• Stewart Massie

Techniques for music recommendation are increasingly relying on hybrid representations to retrieve new and exciting music. A key component of these representations is musical content, with texture being the most widely used feature. Current techniques for representing texture however are inspired by speech, not music, therefore music representations are not capturing the correct nature of musical texture. In this paper we investigate two parts of the well-established mel-frequency cepstral coefficients (MFCC) representation: the resolution of mel-frequencies related to the resolution of musical notes; and how best to describe the shape of texture. Through contextualizing these parts, and their relationship to music, a novel music-inspired texture representation is developed. We evaluate this new texture representation by applying it to the task of music recommendation. We use the representation to build three recommendation models, based on current state-of-theart methods. Our results show that by understanding two key parts of texture representation, it is possible to achieve a significant recommendation improvement. This contribution of a music-inspired texture representation will not only improve content-based representation, but will allow hybrid systems to take advantage of a stronger content component.

IJCAI Conference 2011 Conference Paper

Finding the Hidden Gems: Recommending Untagged Music

• Ben Horsburgh
• Susan Craw
• Stewart Massie
• Robin Boswell

We have developed a novel hybrid representation for Music Information Retrieval. Our representation is built by incorporating audio content into the tag space in a tag-track matrix, and then learning hybrid concepts using latent semantic analysis. We apply this representation to the task of music recommendation, using similarity-based retrieval from a query music track. We also develop a new approach to evaluating music recommender systems, which is based upon the relationship of users liking tracks. We are interested in measuring the recommendation quality, and the rate at which cold-start tracks are recommended. Our hybrid representation is able to outperform a tag-only representation, in terms of both recommendation quality and the rate that cold-start tracks are included as recommendations.

AIIM Journal 2011 Journal Article

Integrating case-based reasoning with an electronic patient record system

• Martijn van den Branden
• Nirmalie Wiratunga
• Dean Burton
• Susan Craw

Electronic patient records (EPRs) contain a wealth of patient-related data and capture clinical problem-solving experiences and decisions. Excelicare is such a system which is also a platform for the national generic clinical system in the UK. Objective This paper presents, ExcelicareCBR, a case-based reasoning (CBR) system which has been developed to complement Excelicare. Objective of this work is to integrate CBR to support clinical decision making by harnessing electronic patient records for clinical experience reuse. Methods CBR is a proven problem solving methodology in which past solutions are reused to solve new problems. A key challenge that we address in this paper is how to extract and represent a case from an EPR. Using an example from the lung cancer domain we demonstrate our generic case representation approach where Excelicare fields are mapped to case features. Once the case base is populated with cases containing data from the EPRs database a standard weighted k-nearest neighbour algorithm combined with a genetic algorithm based feature weighting mechanism is used for case retrieval and reuse. Conclusions We conclude that incorporating case authoring functionality and a generic retrieval mechanism were key to successful integration of ExcelicareCBR. This paper also demonstrates how the application of CBR can enable sharing of lessons learned through the retrieval and reuse of EPRs captured as cases in a case base.

AAAI Conference 2007 Conference Paper

Informed Case Base Maintenance: A Complexity Profiling Approach

• Susan Craw

Knowledge maintenance for Case-Based Reasoning systems is an important knowledge engineering task despite the availability of initial case knowledge and new cases to extend it. For classification systems it is essential that different scenarios for the various classes are well represented and decision boundaries are well defined in the case knowledge. A complexity-based competence metric is proposed that identifies redundant and error-causing cases to be deleted. The metric informs a maintenance tool that enables the engineer to experiment and balance conflicting objectives. Complexityinformed maintenance outperforms benchmark algorithms for redundancy and error reduction tasks.

AIJ Journal 2006 Journal Article

Learning adaptation knowledge to improve case-based reasoning

• Susan Craw
• Nirmalie Wiratunga
• Ray C. Rowe

Case-Based Reasoning systems retrieve and reuse solutions for previously solved problems that have been encountered and remembered as cases. In some domains, particularly where the problem solving is a classification task, the retrieved solution can be reused directly. But for design tasks it is common for the retrieved solution to be regarded as an initial solution that should be refined to reflect the differences between the new and retrieved problems. The acquisition of adaptation knowledge to achieve this refinement can be demanding, despite the fact that the knowledge source of stored cases captures a substantial part of the problem-solving expertise. This paper describes an introspective learning approach where the case knowledge itself provides a source from which training data for the adaptation task can be assembled. Different learning algorithms are explored and the effect of the learned adaptations is demonstrated for a demanding component-based pharmaceutical design task, tablet formulation. The evaluation highlights the incremental nature of adaptation as a further reasoning step after nearest-neighbour retrieval. A new property-based classification to adapt symbolic values is proposed, and an ensemble of these property-based adaptation classifiers has been particularly successful for the most difficult of the symbolic adaptation tasks in tablet formulation.

KER Journal 2005 Journal Article

Design, innovation and case-based reasoning

• Ashok K. Goel
• Susan Craw

The design task is especially appropriate for applying, integrating, exploring and pushing the boundaries of case-based reasoning. In this paper, we briefly review the challenges that design poses for case-based reasoning and survey research on case-based design ranging from early explorations to more recent work on innovative design. We also summarize the theoretical contributions this research has made to case-based reasoning itself.

KER Journal 2005 Journal Article

Retrieval, reuse, revision and retention in case-based reasoning

• Ramon Lopez de Mantaras
• David McSherry
• Derek Bridge
• David Leake
• Barry Smyth
• Susan Craw
• Boi Faltings
• Mary Lou Maher

Case-based reasoning (CBR) is an approach to problem solving that emphasizes the role of prior experience during future problem solving (i.e., new problems are solved by reusing and if necessary adapting the solutions to similar problems that were solved in the past). It has enjoyed considerable success in a wide variety of problem solving tasks and domains. Following a brief overview of the traditional problem-solving cycle in CBR, we examine the cognitive science foundations of CBR and its relationship to analogical reasoning. We then review a representative selection of CBR research in the past few decades on aspects of retrieval, reuse, revision and retention.

AAAI Conference 1999 Conference Paper

Representing Problem-Solving for Knowledge Refinement

• Susan Craw
• Robin Boswell
• The Robert Gordon University

Knowledge refinementtools seek to correct faulty knowledgebased systems (KBSs)by identifying and repairing potentially faulty rules. Thegoal of the KRuSTWorks project is to provide a source of refinement componentsfrom whichspecialised refinementtools tailored to the needs of a range of KBSs are built. A core refinement algorithm reasons about the knowledgethat has been applied, but this approach demands general knowledge structures to represent the reasoning of a particular problemsolving episode. This paper investigates somecomplex formsof rule interaction and defines a knowledgestructure encompassing these. The approach has been applied to KBSs built in four shells andis demonstrated on a small examplethat incorporates someof the complexity foundin real applications.

ICML Conference 1995 Conference Paper

Protein Folding: Symbolic Refinement Competes with Neural Networks

• Susan Craw
• Paul Hutton

ECAI Conference 1990 Conference Paper

Automating the Refinement of Knowledge-Based Systems

• Susan Craw
• Derek H. Sleeman