Explanation Facilities Research Articles

Justification vs. Transparency: Why and How Visual Explanations in a Scientific Literature Recommender System

Significant attention has been paid to enhancing recommender systems (RS) with explanation facilities to help users make informed decisions and increase trust in and satisfaction with an RS. Justification and transparency represent two crucial goals in explainable recommendations. Different from transparency, which faithfully exposes the reasoning behind the recommendation mechanism, justification conveys a conceptual model that may differ from that of the underlying algorithm. An explanation is an answer to a question. In explainable recommendation, a user would want to ask questions (referred to as intelligibility types) to understand the results given by an RS. In this paper, we identify relationships between Why and How explanation intelligibility types and the explanation goals of justification and transparency. We followed the Human-Centered Design (HCD) approach and leveraged the What–Why–How visualization framework to systematically design and implement Why and How visual explanations in the transparent Recommendation and Interest Modeling Application (RIMA). Furthermore, we conducted a qualitative user study (N = 12) based on a thematic analysis of think-aloud sessions and semi-structured interviews with students and researchers to investigate the potential effects of providing Why and How explanations together in an explainable RS on users’ perceptions regarding transparency, trust, and satisfaction. Our study shows qualitative evidence confirming that the choice of the explanation intelligibility types depends on the explanation goal and user type.

Neurules and connectionist expert systems: Unexplored neuro-symbolic reasoning aspects

Neuro-symbolic approaches combine neural and symbolic methods. This paper explores aspects regarding the reasoning mechanisms of two neuro-symbolic approaches, that is, neurules and connectionist expert systems. Both provide reasoning and explanation facilities. Neurules are a type of neuro-symbolic rules tightly integrating the neural and symbolic components, giving pre-eminence to the symbolic component. Connectionist expert systems give pre-eminence to the connectionist component. This paper explores reasoning aspects about neurules and connectionist expert systems that have not been previously addressed. As far as neurules are concerned, an aspect playing a role in conflict resolution (i.e., order of neurules) is explored. Experimental results show an improvement in reasoning efficiency. As far as connectionist expert systems are concerned, variations of the reasoning mechanism are explored. Experimental results are presented for them as well showing that one of the variations generally performs better than the others.

Conversational Recommender Systems Based on Mobile Chatbot for Culinary

Culinary places are one of the tourists attractions in a place that makes many new culinary places appear. Various types of new foods and drinks are present along with the addition of culinary places. However, this can be a problem when tourists visit a new destination and look for a culinary place that suits their tastes. In the previous research on the recommendation system for culinary places, users only gave their preferences at the beginning of the recommendation process and ignored the operating hours of the recommended culinary places. Therefore, we developed a recommendation system for culinary places by utilizing the context of time from users. We use the Conversational Recommender System on the chatbot platform with the Personalized PageRank algorithm to generate recommendations. In addition, we also use the explanation facility to get an explanation of the recommended items. We use questionnaires and the accuracy of recommendation results to measure user satisfaction and system performance. The evaluation results with a questionnaire involving 81 respondents concluded that users are pretty satisfied with the system built. However, testing with accuracy yields a value of 40%, proving that the system performance is low

A Study on the User Experience according to the Method and Detail of Recommendation Agent's Explanation Facilities

A Study on the User Experience according to the Method and Detail of Recommendation Agent's Explanation Facilities

Rule Based Method in Expert System for Detection Pests and Diseases of Corn

Corn is a multi-functional plant, both for direct consumption and as the main raw material for animal feed and the food industry. The need for corn in Indonesia, which continues to increase, needs to be balanced with an increase in production. So that various government policy strategies are carried out, in an effort to increase productivity. Constraints in the cultivation of corn, namely farmers have limitations in identifying diseases that attack plants, and ways to control pests and diseases. The purpose of this study is to propose the use of technology in agriculture by developing an expert system for the detection of corn pests and diseases, which will provide information and strategies for controlling pests and diseases, in order to reduce losses due to crop failure. The knowledge base in expert system contains a set of rules that use the IF-THEN pattern, and to reason on a rule base using forward cahaining method. Expert system is a tool to detection pests and diseases and how to control them like providing expert assistance. In addition, system also provides explanation facility related to the diagnosis results, according to the symptoms obtained from the user. The accuracy detecting pests and diseases 76.6%.

A Study on the User Experience according to the Existence of Explanation Facilities and Individuals Privacy Concern Level

A Study on the User Experience according to the Existence of Explanation Facilities and Individuals Privacy Concern Level

An investigation on the user interaction modes of conversational recommender systems for the music domain

Conversational Recommender Systems (CoRSs) implement a paradigm that allows users to interact in natural language with the system for defining their preferences and discovering items that best fit their needs. CoRSs can be straightforwardly implemented as chatbots that, nowadays, are becoming more and more popular for several applications, such as customer care, health care, and medical diagnoses. Chatbots implement an interaction based on natural language, buttons, or both. The implementation of a chatbot is a challenging task since it requires knowledge about natural language processing and human–computer interaction. A CoRS might be particularly useful in the music domain since music is generally enjoyed in contexts when a standard interface cannot be exploited (driving, doing homeworks, running). However, there is no work in the literature that analytically compares different interaction modes for a conversational music recommender system. In this paper, we focus on the design and implementation of a CoRS for the music domain. Our CoRS consists of different components. The system implements content-based recommendation, critiquing and adaptive strategies, as well as explanation facilities. The main innovative contribution is that the user can interact through different interaction modes: natural language, buttons, and mixed. Due to the lack of available datasets for testing CoRSs, we carried out an in vivo experimental evaluation with the goal of investigating the impact of the different interaction modes on the recommendation accuracy and on the cost of interaction for the final user. The experiment involved 110 people, and 54 completed the whole process. The analysis of the results shows that the best interaction mode is based on a mixed strategy that combines buttons and natural language. In addition, the results allow to clearly understand which are the steps in the dialog that are particularly strenuous for the user.

RESKO: Repositioning drugs by using side effects and knowledge from ontologies

The objective of drug repositioning is to apply existing drugs to different diseases or medical conditions than the original target, and thus alleviate to a certain extent the time and cost expended in drug development. Our system RESKO, REpositioning drugs using Side Effects and Knowledge from Ontologies, identifies drugs with similar side-effects which are potential candidates for use elsewhere, the supposition is that similar side-effects may be caused by drugs targeting similar proteins and pathways. RESKO, integrates drug chemical data, protein interaction and ontological knowledge. The novel aspects of our system include a high level of biological knowledge through the use of pathway and biological ontology integration. This provides a explanation facility lacking in most of the existing methods and improves the repositioning process. We evaluate the shared side effects from the eight conventional Alzheimer drugs, from which sixty-seven candidate drugs based on a side-effect commonality were identified. The top 25 drugs on the list were further investigated in depth for their suitability to be repositioned, the literature revealed that many of the candidate drugs appear to have been trialed for Alzheimer’s disease. Thus verifying the accuracy of our system, we also compare our technique with several competing systems found in the literature.

Tutorial of the probabilistic methods Bayesian networks and influence diagrams applied to medicine.

Unpredictability arises in numerous real-world implementations especially in medical fields, being one of the principal subjects that expert systems have to deal with. Bayesian networks (BNs) allow constructing expert systems by utilizing likelihood as a measure of uncertainty. A BN is a statistical model that yields a graphical description of the probabilistic associations between a group of pertinent variables. Probabilistic reasoning involves computing the posterior probability of the unobserved variables given the accessible evidence, based on the application of the Bayes theorem. The principal benefit from BNs is that intricate relationships are decreased to simpler local dependencies. Graphical models utilization in health economics and medical decision-making has been supported lately. The non-existence of objective data frequently pressures the knowledge engineer to acquire the likelihoods from human experts' estimations, which turns this task laborious. For this logic, a software explanation facility can help the expert and the knowledge engineer through this procedure. In order to depict graphically and approximate a decision problem, a BN can be extended with decision and utility nodes associated with the realization of the random variables. Such model is named influence diagram (ID). The main aim of this article is to present a tutorial of BNs and the decision-theoretic model's IDs applied to medicine, including an explanation of these methods through several theoretical examples and illustrations of studies in the medical literature.

A systematic review and taxonomy of explanations in decision support and recommender systems

With the recent advances in the field of artificial intelligence, an increasing number of decision-making tasks are delegated to software systems. A key requirement for the success and adoption of such systems is that users must trust system choices or even fully automated decisions. To achieve this, explanation facilities have been widely investigated as a means of establishing trust in these systems since the early years of expert systems. With today's increasingly sophisticated machine learning algorithms, new challenges in the context of explanations, accountability, and trust towards such systems constantly arise. In this work, we systematically review the literature on explanations in advice-giving systems. This is a family of systems that includes recommender systems, which is one of the most successful classes of advice-giving software in practice. We investigate the purposes of explanations as well as how they are generated, presented to users, and evaluated. As a result, we derive a novel comprehensive taxonomy of aspects to be considered when designing explanation facilities for current and future decision support systems. The taxonomy includes a variety of different facets, such as explanation objective, responsiveness, content and presentation. Moreover, we identified several challenges that remain unaddressed so far, for example related to fine-grained issues associated with the presentation of explanations and how explanation facilities are evaluated.

Design and development of web enabled fuzzy expert system using rule advancement strategy

This paper reports a new approach for providing intelligence in the expert system for diagnosis of diseases for rose flower. It describes the development of a web-based intelligent disease diagnosis system. This expert system is based on a fuzzy logic approach and the Euclidean distance method. This approach is based on rule advancement strategy. This approach enables the drawing of inferences with the enhanced intelligence. This approach is used in the existing fuzzy technique for inferencing in expert system. The proposed expert system incorporates new features: 1) development of knowledge management platform; 2) dynamic knowledge base creation strategy. The dynamically prompted rules are derived from those diagnosis sessions which resulted in successful decisions. This enables more efficient decision-making in the future sessions; 3) dynamic knowledge acquisition; 4) explanation facility which incorporates the rule firing history and rule explanation generator. This expert system gives an acceptable diagnosis of diseases. The inferences are drawn faster compared to traditional approaches. The proposed expert system which is based on rule advancement strategy has been tested for flower rose.

A Review on Classification of the Urban Poverty Using the Artificial Intelligence Method

Poverty and how it has been assessed and measured is a frequently discussed topic by policy makers and social developers. The identification process in poverty measurement is indeed essential towards acknowledging the poor in the population; hence this needs to be clarified. Malaysia measures poverty by means of poverty line, indicating the unidimensional and inflexible distribution of poor and non-poor especially in urban areas. Many researchers have used fuzzy logic to solve the problem of rigid poor/non-poor dichotomy. This current trend has been able to augment the gap between the rigid and inflexible classification of poor and non-poor. However, there are still several shortcomings that need attention. For instance, the classification of the poor in fuzzy logic that is based on the average income of households still does not cover on the different range of disadvantage on non-monetary items. Based on these trends, ANFIS is proposed to resolve on the highlighted issues. The winning features of ANFIS, which include on simplicity in implementation, understandable explanation facilities through fuzzy rules, and ease of incorporation of both linguistic and numeric knowledge for problem solving may help in producing better result in classification of the urban poor. Essentially, the neural network is proposed to complement the fuzzy system, hence overcoming the limitations of both fuzzy systems and neural networks. As such, ANFIS method is used in this study to better classify on the poor and non-poor compared to fuzzy rule-based system which is lacking in prediction error rate due to too many variables used. However, this method deteriorates from misclassified poverty indicators; hence this study proposed on ensemble ANFIS to produce more accurate and robust classification results. An ensemble model is usually employed to address the problems of over-fitting, high dimensionality or missing features in the training data. Generally, combining multiple classification models increases predictive performance compared to the use of an individual model alone. Therefore, based on these current trends, this study is aimed to do a review on classification of the urban poverty using the artificial intelligence method.

Conversational Recommender System with Explanation Facility Using Semantic Reasoning

<p>Conversational recommender system is system that provides dialogue as user guide to obtain information from the user, in order to obtain preference for products needed. This research implements conversational recommender system with knowledge-based in the smartphone domain with an explanation facility. The recommended products are obtained based on the functional requirements of the user. Therefore, this study use ontology model as a knowledge to be more flexible in finding products that is suitable with the functional requirements of the user that is by tracing a series of semantic based on relationships in order to obtain the user model. By exploiting the relationship between instances of user models, the explanation facility generated can be more natural. Our filtering method uses semantic reasoning with inference method to avoid overspecialization. The evaluation show that the performance of our recommender system with explanation facilities is more efficient than the recommendation system without explanation facility, that can be seen from the number of iterations. We also notice that our system has accuracy of 84%.</p>

Effects of rational and social appeals of online recommendation agents on cognition- and affect-based trust

Online product recommendation agents (RAs) utilize rational and social appeals to enhance their persuasive power. However, the underlying mechanisms of how these various appeals work are still not clear. In this study, a laboratory experiment was conducted to examine the differential effects of explanation facilities and avatar interfaces as instances of rational and social appeals, respectively. We investigated (1) the effects of these appeals on cognition- and affect-based trust, and (2) the distinct persuasive outcomes of cognition- and affect-based trust.The results show that explanation facilities significantly enhance users' cognition-based trust. Meanwhile, avatar interfaces have a significant positive impact on users' affect-based trust, but only for those who rate the avatar as highly professional. Besides, our findings attest to the fact that cognition-based trust mainly delivers the utilitarian value (perceived usefulness), while affect-based trust mainly contribute to the hedonic value (perceived enjoyment) of using a RA.

Fog Forecasting for Melbourne Airport Using a Bayesian Decision Network

Abstract Fog events occur at Melbourne Airport, Melbourne, Victoria, Australia, approximately 12 times each year. Unforecast events are costly to the aviation industry, cause disruption, and are a safety risk. Thus, there is a need to improve operational fog forecasting. However, fog events are difficult to forecast because of the complexity of the physical processes and the impact of local geography and weather elements. Bayesian networks (BNs) are a probabilistic reasoning tool widely used for prediction, diagnosis, and risk assessment in a range of application domains. Several BNs for probabilistic weather prediction have been previously reported, but to date none have included an explicit forecast decision component and none have been used for operational weather forecasting. A Bayesian decision network [Bayesian Objective Fog Forecast Information Network (BOFFIN)] has been developed for fog forecasting at Melbourne Airport based on 34 years’ worth of data (1972–2005). Parameters were calibrated to ensure that the network had equivalent or better performance to prior operational forecast methods, which led to its adoption as an operational decision support tool. The current study was undertaken to evaluate the operational use of the network by forecasters over an 8-yr period (2006–13). This evaluation shows significantly improved forecasting accuracy by the forecasters using the network, as compared with previous years. BOFFIN-Melbourne has been accepted by forecasters because of its skill, visualization, and explanation facilities, and because it offers forecasters control over inputs where a predictor is considered unreliable.

Explaining the operation of a home care system

Purpose – The purpose of this paper is to devise a general solution that allows a policy-based (i.e. rule-based) management system to explain its operation. In particular, a solution has been developed and evaluated in the context of an automated home care system. Design/methodology/approach – The work has built on an existing policy-based management system called Advanced Component Control Enhancing Network Technologies (ACCENT). This includes automated management of home care using two forms of rules: higher-level (user) goals and lower-level (system) policies. These rules can be defined by users (typically carers) to personalise how the system should support the resident. In new work, the system has been extended to include an explanation facility that allows the user to understand the past and future behaviour of the system. Findings – An explanation facility has been created to explain the past and future behaviour of the system. An initial evaluation of this has been carried out with carers. The participants in this evaluation found the facility to be understandable and were able to use it effectively. Research limitations/implications – The work has made a useful extension to the design of policy-based systems in general. The initial evaluation with a limited group of users identified small weaknesses in the explanation facility that will be addressed in future work. The updated approach will then be evaluated with a larger group of users. Practical implications – The enhanced home care system is now more usable and comprehensible, and so will be easier to deploy and maintain. Social implications – The explanation facility has made the home care system more usable and comprehensible for users, and so will enhance its acceptability in future deployment. Originality/value – Although expert systems have long been able to explain their operation, this kind of solution has not previously been attempted for policy-based management systems. The value to end users is that the approach makes automated support of home care more understandable and thus more acceptable and usable.

Query Abduction for ELH Ontologies

With the current upward trend in semantically annotated data, ontology-based data access (OBDA) was formulated to tackle the problem of data integration and query answering, where an ontology is formalized as a description logic TBox. In order to meet usability requirements set by users, efforts have been made to equip OBDA system with explanation facilities. One important explanation tool for DL ontologies, referred to as query abduction, can be formalised as abductive reasoning. In particular, given an ontology and an observation (i.e., a query with an answer), an explanation to the observation is a set of facts that together with the ontology can entail the observation. In this paper, we develop a sound and complete algorithm of query abduction for general conjunctive queries in ELH ontologies. This is achieved through ontology approximation and query rewriting. We implemented a prototypical system using the highly optimized Prolog engine XSB. We evaluated our algorithm over university benchmark ontology and our experimental results show that the system is capable of handling query abduction problems for ontology that has approximately 10 millions ABox assertions.

Modularized Cutting Tool Selection Expert System

This paper is to present a rule-based cutting tool selecting expert system which has knowledge modules and rule bases. Besides, according to different process targets, the selection progress will apply corresponding constraints and rule modules. The logic of tool selection follows a decision-making procedure as an experienced engineers. The strategy of system is to guide the user through several standard steps: information input; feature recognition; selection of machining method; selection of tool material and type; calculation of process parameter and solving cutting problem. This system also has a modularized structure which allows adding new functions and new modules to expand knowledge base and data base. Modules involves in this system are composed of the user interface, knowledge acquisition facility, explanation facility, the knowledge base module, the inference engine and the database module.

초고층 주거 및 숙박시설의 수직동선계획 전문가시스템을 위한 알고리즘 개발

This study has been proceeded based on the idea to develop an expert system for vertical transportation planning in high-rise buildings. Housings and hotels, which are two of the main usages in high-rise buildings, were researched. Components of the system, which are 'database', 'explanation facilities', 'inference engine', and 'knowledge base', were actualized based on information about vertical transportation planning for the studied usages. These contents were materialized to construct an algorithm which can be used for planning high-rise housings and hotels based on simple building information. Through further research, an expert system can be developed to support evaluating and selecting design alternatives economically and efficiently in the process of designing high-rise buildings.

A rule-based method for scalable and traceable evaluation of system architectures

Despite the development of a variety of decision-aid tools for assessing the value of a conceptual design, humans continue to play a dominant role in this process. Researchers have identified two major challenges to automation, namely the subjectivity of value and the existence of multiple and conflicting customer needs. A third challenge is however arising as the amount of data (e.g., expert judgment, requirements, and engineering models) required to assess value increases. This brings two challenges. First, it becomes harder to modify existing knowledge or add new knowledge into the knowledge base. Second, it becomes harder to trace the results provided by the tool back to the design variables and model parameters. Current tools lack the scalability and traceability required to tackle these knowledge-intensive design evaluation problems. This work proposes a traceable and scalable rule-based architecture evaluation tool called VASSAR that is especially tailored to tackle knowledge-intensive problems that can be formulated as configuration design problems, which is demonstrated using the conceptual design task for a laptop. The methodology has three main steps. First, facts containing the capabilities and performance of different architectures are computed using rules containing physical and logical models. Second, capabilities are compared with requirements to assess satisfaction of each requirement. Third, requirement satisfaction is aggregated to yield a manageable number of metrics. An explanation facility keeps track of the value chain all along this process. This paper describes the methodology in detail and discusses in particular different implementations of preference functions as logical rules. A full-scale example around the design of Earth observing satellites is presented.