KMIS 2018 Abstracts


Full Papers
Paper Nr: 5
Title:

How Can Collaborative Augmented Reality Support Operative Work in the Facility Management Industry?

Authors:

Henri Jalo, Henri Pirkkalainen, Osku Torro, Hannu Kärkkäinen, Jukka Puhto and Tuomas Kankaanpää

Abstract: Augmented reality (AR) enables effective knowledge transfer in synchronous and asynchronous modes of collaboration independent of the users’ location. Researchers have emphasized that collaborative characteristics of AR could change how companies carry out knowledge management. However, there is little research about this subject. We address this gap specifically in the context of the facility management (FM) industry. A qualitative multiple-case study was carried out to explore how collaborative AR can bring value to FM companies. This study’s contribution to research is a better understanding of the application of collaborative AR in the context of FM. As a managerial contribution, companies can better understand what type of collaborative AR solutions can be adopted in the short- and long-term. The factors that enable the adoption of these solutions are discussed.

Paper Nr: 6
Title:

Training and Re-using Human Experience: A Recommender for More Accurate Cost Estimates in Project Planning

Authors:

Christian Rudolf von Rohr, Hans Friedrich Witschel and Andreas Martin

Abstract: In many industries, companies deliver customised solutions to their (business) customers within projects. Estimating the human effort involved in such projects is a difficult task and underestimating efforts can lead to non-billable hours, i.e. financial loss on the side of the solution provider. Previous work in this area has focused on automatic estimation of the cost of software projects and has largely ignored the interaction between automated estimation support and human project leads. Our main hypothesis is that an adequate design of such interaction will increase the acceptance of automatically derived estimates and that it will allow for a fruitful combination of data-driven insights and human experience. We therefore build a recommender that is applicable beyond software projects and that suggests job positions to be added to projects and estimated effort of such positions. The recommender is based on the analysis of similar cases (case-based reasoning), “explains” derived similarities and allows human intervention to manually adjust the outcomes. Our experiments show that recommendations were considered helpful and that the ability of the system to explain and adjust these recommendations was heavily used and increased the trust in the system. We conjecture that the interaction of project leads with the system will help to further improve the accuracy of recommendations and the support of human learning in the future.

Paper Nr: 8
Title:

Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders

Authors:

Hans Friedrich Witschel and Andreas Martin

Abstract: We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.

Paper Nr: 21
Title:

Investigating Knowledge Management in the Software Industry: The Proof of Concept’s Findings of a Questionnaire Addressed to Small and Medium-sized Companies

Authors:

Danieli Pinto, Mariana Oliveira, Flávio Bortolozzi, Nada Matta and Nelson Tenório

Abstract: The software industry is dynamic and complex, so they need to use the knowledge to excel in a highly competitive market. Thus, the knowledge well managed brings the organization a sustainable and competitive advantage. Knowledge Management (KM) processes can avoid knowledge lost since they provide knowledge flow for the whole organization. These processes are supported by practices and tools promoting the creation, retention, and dissemination of the knowledge within the organizational environment. The objective of this study was to validate, through a proof of concept (POC), a questionnaire to investigate the processes, practices, and tools of KM in SME-Soft. The questionnaire was evaluated by fifty-one professionals and KM experts from the software industry. Our findings point out that the questionnaire is suitable for the software industry.

Paper Nr: 30
Title:

Tag Recommendation for Open Government Data by Multi-label Classification and Particular Noun Phrase Extraction

Authors:

Yasuhiro Yamada and Tetsuya Nakatoh

Abstract: Open government data (OGD) is statistical data made and published by governments. Administrators often give tags to the metadata of OGD. Tags, which are a collection of a single word or multiple words, express the data. Tags are useful to understand the data without actually reading the data and also to search for OGD. However, administrators have to understand the data in detail in order to assign tags. We take two different approaches for giving appropriate tags to OGD. First, we use a multi-label classification technique to give tags to OGD from tags in the training data. Second, we extract particular noun phrases from the metadata of OGD by calculating the difference between the frequency of a noun phrase and the frequencies of single words within the noun phrase. Experiments using 196,587 datasets on Data.gov show that the accuracy of prediction by the multi-label classification method is enough to develop a tag recommendation system. Also, the experiments show that our extraction method of particular noun phrases extracts some infrequent tags of the datasets.

Paper Nr: 38
Title:

Exploring RDF Datasets with LDscout

Authors:

Anna Goy, Diego Magro and Francesco Conforti

Abstract: In this paper, we present the formal model underlying LDscout, a Java library enabling developers to query a dataset specifying the vocabulary (ontology) they want to use and the instances they want to query about. The model is based on the formal definition of the concepts of Exploration Task and Exploration Task Solution, and is independent from the dataset. In this paper, we present the specific implementation that enables the interaction with RDF triplestores using OWL ontologies. In order to assess our approach, we report the usage of LDscout within PRiSMHA, a Digital Humanities project aimed at enhancing the access to historical archives through Semantic Web technologies.

Short Papers
Paper Nr: 7
Title:

How Territorial Knowledge Effects on the Sustainable Development within Companies

Authors:

Amer Ezoji and Nada Matta

Abstract: Nowadays sustainability is issued to industries in order to integrate it into their activities for sustainable development. Studying of territorial resources impact on industrial activities and decision makers’ information when considering sustainability. The aim is to enhance the knowledge of actors in the industries in relation to territorial resource through sustainable objective. Moreover, considering how this knowledge can help to the different level of industry in regard to value creation for human and decision making. This consideration is done by categorizing of territorial knowledge and linking them with other classes and industrial organization.

Paper Nr: 11
Title:

The Fake News Challenge: Stance Detection using Traditional Machine Learning Approaches

Authors:

Razan Masood and Ahmet Aker

Abstract: Fake news has caused sensation lately, and this term is the Collins Dictionary Word of the Year 2017. As the news are disseminated very fast in the era of social networks, an automated fact checking tool becomes a requirement. However, a fully automated tool that judges a claim to be true or false is always limited in functionality, accuracy and understandability. Thus, an alternative suggestion is to collaborate a number of analysis tools in one platform which help human fact checkers and normal users produce better judging based on many aspects. A stance detection tool is a first stage of an online challenge that aims to detect fake news. The goal is to determine the relative perspective of a news article towards its title. In this paper, we tackle the challenge of stance detection by utilizing traditional machine learning algorithms along with problem specific feature engineering. Our results show that these models outperform the best outcomes of the participating solutions which mainly use deep learning models.

Paper Nr: 12
Title:

Transformation Method from Scenario to Sequence Diagram

Authors:

Yousuke Morikawa, Takayuki Omori and Atsushi Ohnishi

Abstract: Both scenario and sequence diagram are effective models for specifying behaviours of the target systems. Scenarios can be used for requirements elicitation in the requirements definition. Sequence diagrams can be used for interactions between a system user and system, and between objects. If these two models specifying behaviours of the same system, these models should be consistent. In this paper, we propose a transformation method from a scenario written with a structured scenario language named SCEL to a sequence diagram written with PlantUML. The transformation method will be illustrated with an example.

Paper Nr: 15
Title:

Looking into Big Data: The Case of the U. S. Federal Government

Authors:

Sherry L. Xie

Abstract: This paper reports on a study that aimed to examine the term big data for its meaning in a particular setting. The study chose the U.S. Federal Government as its case and analysed all the big data projects and programs identified as representative of the U.S. Big Data Initiative. It constructed an analytical framework and generated findings in forms of statistic descriptions and narrative discussions. The study discovered that 1) not all the big data projects and programs possess in a collective manner the typical 3 Vs (i.e., volume, variety, and velocity), 2) variety appears to be the most valued characteristic, and 3) to-be-collected data lags largely behind existing data, indicating that technologies such as the Internet of Things are still at the stage of being developed. It also unrevealed that the U.S. Federal Government’s current big data focus is heavily placed on IT and the term big data has made that focus hidden. It then suggests to sufficiently distinguish data and the technologies underlying the various features of data so that collaborations between the owners of data and technologies can be forged with easiness and big data benefits can be realized with efficiency and effectiveness.

Paper Nr: 18
Title:

Knowledge Management Strategy in the Non-profit Sector: A Case Study at a UK Heritage Site

Authors:

Roger Fullwood and Jennifer Rowley

Abstract: The purpose of this article is to explore knowledge management strategy in a large heritage site that is heavily dependent on volunteers. A single site case study approach was utilised and rich qualitative data was generated by interviews with departmental managers. The results of the research suggested that a strong culture of knowledge sharing existed at the site and that it was broadly supportive of the knowledge management strategy. Tacit knowledge was shared extensively within and across volunteer groups and there was evidence of the operation of communities of practice. The outcome of these processes was substantial individual and organisational learning. However, knowledge sharing by managers with volunteers was more prescriptive in some outdoor roles. Managers were also mindful of the need for consistency and accuracy in the knowledge shared with volunteers in order to ensure the provision of a uniform service to the public that was consistent with organisational values. An initiative to promote a volunteer intranet was however less successful.

Paper Nr: 26
Title:

Exploratory Study on the Adoption of Knowledge Management Practices in Small Medium Enterprises in Resource Constrained Areas: A Case Study of the Dairy Industry in Uganda

Authors:

Theodora Mwebesa Twongyirwe and Jude Lubega

Abstract: The aim of this paper is to shed light on Knowledge Management (KM) practices in Small Medium enterprises (SMEs) in resource constrained areas. The Paper presents the results of an exploratory study investigating the adoption of KM practices in 66 enterprises across the Dairy industry located in South-western Uganda. The Methodology adopted focused on literature review to gain an in-depth understanding KM in SMEs and insight into the Dairy industry in Uganda, a structured questionnaire was used to collect information from the different stakeholders and an interview guide used to conduct interviews with various stakeholders in the firms. The results show that SMEs are falling behind large companies in developing KM practices; however all the firms showed a significant understanding of the benefits of KM. There is significantly low skills and usage of ICT in SMEs which is essential for successful implementation of KM within an organization. Web browsing, voice and SMS are the most commonly used ICT Services and the least used are ICT professional services like business intelligence tools, ERPs and Dashboards, which creates significant opportunity for development of KM tools suitable for resource constrained areas. Skills gap, informal knowledge and technological barriers where highlighted as significant barriers to implementation of KM. There is limited usage of Decision Support Systems and Data mining tools as KM Tools.

Paper Nr: 28
Title:

Women and Technologies: Towards a Gendered Profile of Digital Do-It-Yourself Workers?

Authors:

Carolina Guerini, Eliana Minelli and Aurelio Ravarini

Abstract: Though yet partly unexplored, Digital Do-It-Yourself (DiDIY) is both an objective phenomenon that can be investigated from the point of view of its output and a subjective phenomenon that shapes individual behaviors and can be analyzed from the perspective of competences, motivations and social relationships. DiDIY is a complex socio-technical phenomenon that heavily impacts on organizations. Following recent research paths aimed at defining the subjective side of DiDIY, this research focuses on the gendered DiDIYer’s profile. Female DiDIYers’ personal characteristics seem to confirm previous studies dealing with the general DiDIYer’s profile (Guerini and Minelli, 2018). They are digitally literate and aware of their skills, curious and eager to innovate. Proud and conscious of their potential contribution to the improvement of their lives and their workplace, open to professional and personal challenges, they qualify themselves as expert amateur, not just as pure technology adopters. Female DiDIYers are involved in organic and participative cultures and their roles are characterised by knowledge sharing and creation, also through communities of practice. Female DiDIY is concentrated in complex roles, which link the organization to the external environment, being intrinsically autonomous in their expression and far from clerical activities.

Paper Nr: 34
Title:

Digital Social Matching Ecosystem for Knowledge Work

Authors:

Jukka Huhtamäki and Thomas Olsson

Abstract: Knowledge work involves various so-called social matching decisions: who to recruit, who to pair up or team up, who to ask for consultancy, etc. Despite the scale of effects such decisions can have on organizations, social matching activities are little supported by technology. In this position paper, we describe an ongoing venture to develop the enablers and a shared vision for forming digital ecosystems around social matching of knowledge workers. Rather than developing monolithic, organization-specific systems, we argue for an API-based ecosystemic approach that helps co-create value and develop more networked, innovative, and viable business ventures. We elaborate our vision and work-in-progress by presenting requirements for and scenarios of digital ecosystems for social matching in knowledge work.

Paper Nr: 36
Title:

ABCT: The Activity based Contextual Tagging Ontology

Authors:

Grégory Bourguin and Arnaud Lewandowski

Abstract: A large amount of applications now includes tagging mechanisms that have proven efficiency to organize, navigate through, retrieve, and discover online resources. However, despite the valuable research work done to improve these solutions, the literature shows that a further step has to be done in order to better consider the contexts in which tagging actions occur. In this paper, we define a list of elements constituting a tagging context that should be considered in order to better give access to the knowledge shared through users’ taggings. We propose an ontological model named ABCT (Activity Based Contextual Tagging) for describing these contexts. ABCT takes benefits from the many research in tagging ontologies and that are synthetized in MUTO (Modular Unified Tagging Ontology). ABCT marries MUTO and PROV (Provenance) concepts to facilitate the description of tags and tagging contexts, essentially through to the notions of Tagging and Activity.

Paper Nr: 39
Title:

Does Investment in Digital Technologies Yield Digital Business Value? The Digital Investment Paradox and Knowledge Creation as Enabling Capability

Authors:

Christian Riera and Junichi Iijima

Abstract: This paper explores whether the investments in Digital Technologies relate to Business Value in organizations and the role of Knowledge Creation. To evaluate this, data collected from Japanese Small and Medium Enterprises from “Competitive IT Strategy SME Selection 100” list of 3 years was analysed by correlation, regression and general linear model analysis. The direct effect that investment in Digital Technologies had on Business Value was observed for Learning & Growth objectives. The influence that the four processes of Knowledge Creation (SECI Model) had was explored and found that Combination process was positively related with the investment in Digital Technologies for Financial and Learning & Growth objectives. Externalization had a negative relationship with the investment in Financial objectives. Although not verified statistically, a trend showed organizations with higher Knowledge Creation Capabilities gained higher benefits from investment in Digital Technologies as the investment increased and vice versa. Although the limitations of this study are related to the population characteristics and responses’ reliability, it was considered that the potential insights were valuable enough to overcome such limitations. With this empirical study the concern of “Digital Investment Paradox” is raised and the debate is initiated with Knowledge Creation as an enabling capability.

Paper Nr: 40
Title:

Information Models and Information Exchange in Plant-wide Monitoring and Control of Industrial Processes

Authors:

David Hästbacka, Petri Kannisto and Matti Vilkko

Abstract: The efficiency of industrial processes depends on how well the processes can be controlled and this affects the quality, use of resources as well as the environmental impact. Advanced monitoring and control solutions for large-scale industrial processes require information from different systems. The challenge in integration is diverse messaging structures and lack of common semantics in exchange of information between related information systems as well as their human operators. This paper provides a comparison of some of the existing standards of the domain defining suitable structures. Based on these, a model for data and event message structures is developed. The approach builds on a separation of concerns keeping the messaging semantics independent of the transport layer. The requirement is to enable also asynchronous communication as adapters are often needed in distributed environments with heterogeneous systems and communication protocols. The developed structures have been found suitable for communicating measurements and events in industrial process settings as shown by case examples.

Paper Nr: 43
Title:

An Unified Representation of Source Code Authoring Workflows

Authors:

Dmitrii Timofeev and Alexander Samochadin

Abstract: Existing approaches to modeling software development processes mostly deal with high-level processes at the level of project management. There are specific tasks that involve the analysis of processes at the level of writing and modifying the program code, but they lack a common reusable modeling framework. We suggest that a model of source code editing workflow would be beneficial for many tasks, from defect prediction to teaching programming to novices. We propose a unified approach that combines several levels of annotations, from keyboard events to task tracker issues and project planning.

Posters
Paper Nr: 3
Title:

Technology Enhanced Learning using Virtual and Augmented Realities: An Applied Method to Improve the Animation Teaching Delivery

Authors:

Rosana Marar and Edward Jaser

Abstract: This paper presents a software solution to enhance the content and presentation of graphic design and animation related textbooks. Using augmented and virtual reality concepts, a mobile application is developed to improve the static material found in books. This allows users to interact with animated examples and tutorials using their mobile phones and stereoscopic 3D viewers which will enhance information delivery. The application is tested on Google Cardboard with visual content in 3D space. Evaluation of the proposed application demonstrates that it improved the readability of static content and provided new experiences to the reader.

Paper Nr: 10
Title:

Picking Process Variability in Small and Medium-Sized Enterprises: State of the Art and Knowledge Modeling

Authors:

Daniel Hilpoltsteiner, Stephanie Bäuml and Christian Seel

Abstract: Information modelling is an established standard for knowledge representation in companies. However, small and medium-sized companies (SME) often lack the resource to use it for their own purpose. In this paper a solution to model business process variability in order picking processes is discussed. Therefore we did a knowledge extraction from different companies using a questionnaire, expert interviews and workshops with different experts from the field of production logistics in SME has been done. Based on their knowledge different variants of order picking processes in SME were defined and put together in an adaptive process model. Using configuration terms to enrich the adaptive process model allows the distinction between these different variants. Based on different influencing factors a specific process variant can be generated from the process model using element selection and further process optimizations including introducing new technologies can be made.

Paper Nr: 16
Title:

Towards an Exploration of Several Dimensions in Learning: Application on Crisis Management

Authors:

Sammy Teffali, Nada Matta and Eric Châtelet

Abstract: A crisis is a complex situation, which actors have some difficulties to manage it. They are under stress to deal with problems that they cannot predict consequences. The human conditions (familial and life) and, the influence of the environment (politic, economic, media) pushes the actors to lose control of the crisis situation. The question we face in this paper is: “is it possible to predict stress impact situations based on experience feedback?” “Is it possible to use this type of prediction for learning?” Our main hypothesis to represent experience feedback in a situation prediction in order to show negative consequences and correctness actions is taken account. Fuzzy theory concept is used in prediction in order to generate several situations and allow learners to explore different options.

Paper Nr: 17
Title:

Semantic Representation of Information by Ontological Networks to Improve Knowledge Management in Higher Education

Authors:

Roberto A. García-Vélez, Jorge Andrés Galán-Mena, Ahmed Dahroug, Vladimir E. Robles-Bykbaev and Martín López-Nores

Abstract: Institutions of Higher Education (IHE) seek to respond to new ways of conceiving and projecting higher education embodied in the profile of a professional. Faced with this challenge, educational models focus mainly on the theoretical-practical references of critical training, constructivism and collaborative learning. Although there are several knowledge management solutions in the field of higher education, which have managed to formalize the organizational structure of academic institutions in ontologies, so far none of these proposals divides and makes explicit the development that the actors of the ecosystem (students and educators) take over time. Our proposal is to construct a semantic representation of the academic ecosystem by implementing an ontological network that allows managing the knowledge generated in a more efficient way. This architecture is intended to be used as an instrument to support the academic body and for the centralization of information. To achieve our objective, we carry out a reengineering process of relevant institutional documents, such as the academic record of the students, in each of their facets of learning. We have interviewed specialists in the area and reuse academic domain ontologies to form a consistent knowledge base.

Paper Nr: 41
Title:

Crypto-voting, a Blockchain based e-Voting System

Authors:

Francesco Fusco, Maria Ilaria Lunesu, Filippo Eros Pani and Andrea Pinna

Abstract: In most of the electing contexts, the secrecy of votes is mandatory. This constraint is unnecessary in the phase of signatures collection which, by nature, are publicly available. This phase precedes, for instance, the popular initiative referendums, or the composition of the electoral rolls. In past, many electronic election systems (or e-voting systems) failed because they were not able to guarantee the total security respect to the vote privacy protection, especially in the long-medium term and in the cases of brute force attacks. The purpose of this study is the presentation and the definition of a new e-voting system named Crypto-voting. We base this solution upon the Shamirs secret sharing approach, implemented using the blockchain technology. We use this technology to integrate the management procedures of the phases and events of an election. These events include the set-up of the system, the distribution of credentials, the voting, the collection of ballot papers, the counting of preferences, the publication of results, and so on. In addition, our system aims to improve the methods of traceability and audit about voting operations, with no middleman.