Christian Severin Sauer

Extracting knowledge from web communities and linked data for case-based reasoning systems

Web communities and the Web 2.0 provide a huge amount of experiences and there has been a growing availability of Linked Open Data. Making experiences and data available as knowledge to be used in case-based reasoning CBR systems is a current research effort. The process of extracting such knowledge from the diverse data types used in web communities, to transform data obtained from Linked Data sources, and then formalising it for CBR, is not an easy task. In this paper, we present a prototype, the Knowledge Extraction Workbench KEWo, which supports the knowledge engineer in this task. We integrated the KEWo into the open-source case-based reasoning tool myCBR Workbench. We provide details on the abilities of the KEWo to extract vocabularies from Linked Data sources and generate taxonomies from Linked Data as well as from web community data in the form of semi-structured texts.

Knowledge Formalisation for Hydrometallurgical Gold Ore Processing

This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective of this knowledge formalisation effort is to create a case-based reasoning application for recommending a treatment process of gold ores. We describe a twofold approach to formalise the necessary knowledge. First, formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. The second aspect of our approach formalises empirical knowledge on hydrometallurgical treatments. The latter, not described in this paper, will enable us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with the formalisation of knowledge in the gold ore refinement domain are the diversity and the amount of parameters used in literature and by experts to describe a mining context. We demonstrate how similarity knowledge was used to formalise literature knowledge. The evaluation of data gathered from experiments with an initial prototype workflow recommender, Auric Adviser, provides promising results.

Two-Phased Knowledge Formalisation for Hydrometallurgical Gold Ore Process Recommendation and Validation

This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective was to create a case-based reasoning application for recommending and validating a treatment process of gold ores. We describe a twofold approach. Formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. Secondly, empirical knowledge on hydrometallurgical treatments is formalised. This enabled us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with formalisation of knowledge in the domain of gold ore refinement are the diversity and the amount of parameters used in literature and by experts to describe a mining context. We demonstrate how similarity knowledge was used to formalise literature knowledge. The evaluation of data gathered from experiments with an initial prototype workflow recommender, Auric Adviser, provides promising results.

Recommending Audio Mixing Workflows

This paper describes our work on Audio Advisor, a workflow recommender for audio mixing. We examine the process of eliciting, formalising and modelling the domain knowledge and expert’s experience. We are also describing the effects and problems associated with the knowledge formalisation processes. We decided to employ structured case-based reasoning using the myCBR 3 to capture the vagueness encountered in the audio domain. We detail on how we used extensive similarity measure modelling to counter the vagueness associated with the attempt to formalise knowledge about and descriptors of emotions. To improve usability we added GATE to process natural language queries within Audio Advisor. We demonstrate the use of the Audio Advisor software prototype and provide a first evaluation of the performance and quality of recommendations of Audio Advisor.

Solution mining for specific contextualised problems: towards an approach for experience mining

In this paper we describe the task of automated mining for solutions to highly specific problems. We do so under the premise of mapping the split view on context, introduced by Brézillon and Pomerol, onto three different levels of abstraction of a problem domain. This is done to integrate the notion of activity or focus and its influence on the context into the mining for a solution. We assume that a problems context describes key characteristics to be decisive criteria in the mining process to mine successful solutions for it. We further detail on the process of a chain of sub problems and their foci adding up to a meta problem solution and how this can used to mine for such solutions. Through a guiding example we introduce basic steps of the solution mining process and common aspects we deem interesting to be analysed closer in upcoming research on solution mining. We further examine the possible integration of these newly established outlines for automatic solution mining for highly specific problems into a SEASALTexp, a currently developed architecture for explanation-aware extraction and case-based processing of experiences from Internet communities. We thereby gained first insights in issues occurring while trying to integrate automatic solution mining.

Web Community Knowledge Extraction for myCBR 3

The current development of web communities and the Web 2.0 provide a huge amount of experiences. Making these experiences available as knowledge to be used in CBR systems is a current research effort. The process of extracting such knowledge from the diverse data types used in web communities and formalising it for CBR is not an easy task. In this paper we present the knowledge extraction workbench prototype KEWo and also review some of the challenges we were facing while integrating it into the case-based reasoning tool myCBR 3.

Explanation-aware design of mobile myCBR-based applications

This paper focuses on extending the explanation capabilities of the myCBR SDK as well as on the optimisation of the myCBR SDK in the context of Android-based mobile application development. The paper examines the available knowledge for explanation generation within context-aware CBR systems. The need for the integration of new explanation capabilities is then demonstrated by an Android-based context- and explanation-aware recommender application. Upon the experience gathered during implementation of the prototype a process for the integration of explanation capabilities into the myCBR SDK is introduced. Additionally, constraints and requirements for the integration of explanation capabilities into myCBR are introduced. Within this process we distinguish domain dependent and domain independent knowledge. We do this with regard to the different requirements for the integration of explanation capabilities into myCBR for the two types of knowledge. The paper further details on our on-going effort to adapt the myCBR SDK for use on the Android platform.

Using case-based reasoning to detect risk scenarios of elderly people living alone at home

In today’s ageing societies, the proportion of elderly people living alone in their own homes is dramatically increasing. Smart homes provide the appropriate environment for keeping them independent and, therefore, enhancing their quality of life. One of the most important requirements of these systems is that they have to provide a pervasive environment without disrupting elderly people’s daily activities. The present paper introduces a CBR agent used within a commercial Smart Home system, designed for detecting domestic accidents that may lead to serious complications if the elderly resident is not attended quickly. The approach is based on cases composed of event sequences. Each event sequence represents the different locations visited by the resident during his/her daily activities. Using this approach, the system can decide whether the current sequence represent an unsafe scenario or not. It does so by comparing the current sequence with previously stored sequences. Several experiments have been conducted with different CBR agent configurations in order to test this approach. Results from these experiments show that the proposed approach is able to detect unsafe scenarios.

Hierarchical Semantic Representations of Online News Comments for Emotion Tagging Using Multiple Information Sources

With the development of online news services, users now can actively respond to online news by expressing subjective emotions, which can help us understand the predilections and opinions of an individual user, and help news publishers to provide more relevant services. Neural network methods have achieved promising results, but still have challenges in the field of emotion tagging. Firstly, these methods regard the whole document as a stream or bag of words and can’t encode the intrinsic relations between sentences. So these methods cannot properly express the semantic meaning of the document in which sentences may have logical relations. Secondly, these methods only use semantics of the document itself, while ignoring the accompanying information sources, which can significantly influence the interpretation of the sentiment contained in documents. Therefore, this paper presents a hierarchical semantic representation model of news comments using multiple information sources, called Hierarchical Semantic Neural Network (HSNN). In particular, we begin with a novel neural network model to learn document representation in a bottom-up way, capturing not only the semantics within sentence but also semantics or logical relations between sentences. On top of this, we tackle the task of predicting emotions for online news comments by exploiting multiple information sources including the content of comments, the content of news articles, and the user-generated emotion votes. A series of experiments and tests on real-world datasets have demonstrated the effectiveness of our proposed approach.

A self-organizing algorithm for community structure analysis in complex networks

Community structure analysis is a critical task for complex network analysis. It helps us to understand the properties of the system that a complex network represents, and has significance to a wide range of real applications. The Label Propagation Algorithm (LPA) is currently the most popular community structure analysis algorithm due to its near linear time complexity. However, the performance of the LPA has proven to be unstable and the correctness of community assignment of nodes is unsatisfactory. In this paper a Self-Organizing Community Detection and Analytic Algorithm (SOCDA2) based on swarm intelligence is proposed. In the algorithm, a network is modeled as a swarm intelligence system, while each node within the network acts iteratively to join or leave communities based on a set of pre-defined node action rules, in order to improve the quality of the communities. When there is not a node changing its belonging community anymore, an optimal community structure will emerge as a result. A variety of experiments conducted on both synthesized and real-world networks have shown results which indicate that the proposed algorithm can effectively detect community structures and the performance is better than that of the LPA. In addition, the algorithm can be extended for overlapping community detection and be parallelized for large-scale network analysis.