Knowledge Requirements for Sustainable Smart Service Design

Jesus Mario Verdugo Cedeño

, Lea Hannola

and Ville Ojanen

School of Engineering Science, Department of Industrial Engineering and Management, LUT University,

Yliopistonkatu 34, Lappeenranta, Finland

Keywords: Service Ecosystem, Knowledge Requirements, Text Mining, Service Design, Service Lifecycle.

Abstract: Recent research have addressed the topic of smart services from distinct angles, covering both technical and

business aspects. However, a holistic approach in development processes of such services have yet to be fully

covered. Therefore, this paper proposes an elicitation of requirements process as the initial step of a smart

service design approach. The process takes information and knowledge needs as its core element for

development, also considering customer centricity, service lifecycle, and sustainability concerns. A text

mining tool was used to discover the unknown knowledge requirements from different text-data sources

presented in a case ecosystem. After a co-occurrence analysis performed by our text mining software, we

extracted the most relevant natural linguistic elements, which are expressed as knowledge requirements. The

proposed elicitation process aims to lay the foundations for further propositions with a holistic point of view.

Future research could aim the application of other technologies and methods for service design, as well as a

broader approach in business processes and interdisciplinary cooperation.

1 INTRODUCTION

The more connected world and accessibility of

resources have driven a seamless spread of ideas and

information in a globalized market. It is leading into

a relative easiness in imitation of product design,

resulting in a commoditization of tangible goods

(Stickdorn et al., 2018). This challenge creates a need

for innovation for organizations, guiding them to turn

their vision into services (Lüftenegger et al., 2017).

Value co-creation is hardly conceived without the

consideration of collaborative partnering interactions

between stakeholders from different organizations

(Lempinen and Rajala, 2014). Such collaborations are

known as service ecosystems, which are considered

as dynamic systems of connected actors interacting

each other through value co-creation, with the ability

of self-reconfiguring continuously (Vargo and Lusch,

2011, Lusch and Nambisan, 2015). Finally, a service

platform serves as the means to integrate actors and

resources of a service ecosystem for service exchange

(Hein et al., 2018).

https://orcid.org/0000-0001-5394-9568

https://orcid.org/0000-0002-9079-7839

https://orcid.org/0000-0001-8124-5082

Service design can be defined as a “human-

centered, collaborative, interdisciplinary and

iterative approach to create experiences that meets

stakeholders needs” (Stickdorn et al., 2018, p. 20),

usually through the approach of design thinking.

Design thinking is a collaborative approach of cross-

functional teams integrated by members from

different backgrounds (Lim et al., 2018). It

concentrates most of the attention on customer

centricity, utilizing tools such as customer journeys

and service blueprints (Bitner et al., 2008). Despite

being a proven approach for service design, it is not

clear how design thinking considers the design

process from a lifecycle point of view, where

“sustainability (environment, social, economic)

value” (Orellano et al., 2018) is approached, most

known as lifecycle thinking (Bauer et al., 2008). On

the other hand, lifecycle perspectives lack customer

centricity on their frameworks (Antikainen and

Valkokari, 2016, Orellano et al., 2018). Therefore, an

integrated process which considers both customer

centricity and sustainability matters should be

researched more in detail.

Cedeño, J., Hannola, L. and Ojanen, V.

Knowledge Requirements for Sustainable Smart Service Design.

DOI: 10.5220/0008069201950202

In Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2019), pages 195-202

ISBN: 978-989-758-382-7

195

The concept of “Smart Services” has gained

attention in recent years due to the digitalization of

industries. Several authors have defined the term to

refer data-driven services (Kim et al., 2018, Lim et

al., 2018, Neuhüttler et al., 2018). However, there is

not an official definition. Data is considered the raw

material or input needed to develop Smart Services.

Hence, it is fundamental to understand the methods,

technologies, and processes required to achieve the

collection and analysis required to transform raw data

to actual knowledge (Fayyad et al., 1996). There are

several approaches to convert data into knowledge,

for both qualitative and quantitative data. One of the

qualitative ones is text mining, which is a knowledge

discovery process to obtain unknown insights from

data contained in texts (Bird et al., 2009). According

to Lim and Maglio (2018), using text mining could

enhance the data collection and analysis of keywords

from different sources and related to the

characteristics (features, needs, pain points,

requirements, experiences) of a given service.

The present study aims to utilize text mining as

the means to determine the unknown knowledge

requirements from the data generated by

stakeholders’ service interactions. The purpose of this

paper is to present a requirements elicitation process

for the initial phases of a smart service design

method, considering the customer centricity and

service lifecycle. The organization of this paper is

presented as follows: Section 2 presents a literature

review of the relevant theory related to smart services

design and applicability of text mining tools. As well

as a brief description of text data mining and its role

on determining service keywords; Section 3

illustrates in detail the requirements elicitation

process proposition, the justification of the chosen

approach and the gaps filled through its application;

Section 4 describes the utilized research method of

case study to demonstrate and justify the applicability

of text mining for requirements discovery; Section 5

discusses the results of the case study and the

requirements elicitation process; and Section 6

concludes with the limitations, practical and

theoretical contributions, as well as its future research

approaches of the study.

2 LITERATURE REVIEW

2.1 Smart Service Design

The most novel approaches for service design

surged to the field with a strong focus on data,

human centricity, collaboration, user experience,

sustainability, lifecycle, and ecosystems. For this

paper, the main focus of study are the service

offerings which take data as their raw material and

outcome, best known as smart services. Such

services are defines by Neuhüttler et al. (2018) as a

self-configurable bundle of digital and physical

services based on data collected from different

sources.

Recently, authors have proposed tools, method

and frameworks covering the novel approaches

mentioned above. First, there is the method suggested

by Kim et al. (2018), which address the data

collection gap of interviews, surveys, and

experiments by collecting customer and business data

from electronic sources. Second, Stickdorn et al.

(2018) aim to deliver a service design based on

customer experiences, with roots in collaborative

design thinking and an ecosystem point of view.

Third, Orellano et al. (2018) propose a framework for

PSS offerings with a lifecycle and sustainable

perspective. It contemplates all the phases of PSS

lifecycle: Beginning of Life (BOL), Middle of Life

(MOL) and End of Life (BOL) (Orellano et al., 2018).

BOL phases consider PSS design, production and

distribution; MOL phases the PSS use, repair and

maintenance; and finally EOL phases involve

disposal and backtracking processes. Such

framework utilizes the lifecycle thinking method,

which is defined by the “ability to decouple the

lifecycle of any offer into sub-processes” (Orellano et

al., 2018, p. 293), translating them into environmental

and societal requirements.

All the approaches follow the current trends of

service design separately. However, there is a

significant research gap of proposing a framework,

method, approach or a process for smart service

design, which considers and integrates the aspects

covered by the previous authors.

2.2 Text Mining as a Tool to Obtain

Knowledge Requirements

As suggested by Kim et al. (2018) the service design

process consists of the following five steps: (1)

Definition of service objectives. A multidisciplinary

agreement is required in order to define the market

trends and constraints, as well as a precise definition

of stakeholders’ objectives. (2) Data collection of

customers’ data sources. The common methods

usually utilize traditional tools for data collection,

such as surveys, or experiments. However, recent

studies have been using data collection from

electronic sources to overcome the bias and trends

from previous sources, e.g., text documents, social

KMIS 2019 - 11th International Conference on Knowledge Management and Information Systems

196

media, data from sensors, emails, and so on

(Ordenes et al., 2014). (3) Analysis of data

collection using both quantitative and qualitative

methods, as well as IT related tools such as big data

analytics and machine learning for requirements

elicitation. For example, the study presented by

Mankad et al. (2016), aims the utilization of

automated text analysis tools for understanding

customers’ reviews. (4) Idea generation for service

propositions. This step also considers the

multidisciplinary approach to reach an agreement of

what are the options that best meet the requirements

of customers. (5) Concept generation. In this final

step, the ideas that best suit the customers’ demands

from the previous step are selected for prototyping

and market test.

For Stickdorn et al. (2018) data collection task

should include different types of data outputs in

order to get a more plentiful and comprehensive

researcher’s findings, known as Data Triangulation.

The terms refers to the principle of combining

distinct data sources, such as text in the form of

documents, transcripts, interviews, audio

translations, notes; images, photos and pictures;

audios, videos; artifacts in the form of brochures,

flyers; tickets and finally quantitative data such as

statistics, tables, numbers, and so on. One of the

most common processes for working with

qualitative data is the Qualitative Content Analysis

(Hsieh, 2005), which interprets and codifies data

from text sources to find patterns and meanings from

them. A regular challenge of text data is its lack of

structure, given its degree of difficulty of analysis

and interpretation (Orellano et al., 2018, Ordenes et

al., 2014). Meanwhile, structured data in the form of

numbers have been a convenient path of

organizations to evaluate a product or service by

giving numerical ponderations to their attributes,

being questionnaires the most traditional method for

customer feedback (Macdonald, 2011).

Text mining or text data mining is the process to

discover unknown knowledge by the analysis of

textual information, finding its structure and hidden

meaning (Mikroyannidis, 2006, Bird et al., 2009). It

is a continually evolving technology which

integrates machine learning algorithms, data

mining, natural language processing and knowledge

management (Yu, 2011, Lim and Maglio, 2018). For

structuring text data, data mining utilizes a

processing method to extract the so-called concepts,

which are words or complete sentences explaining a

general interpretation of a text (Mikroyannidis,

2006).

Several studies have used the text mining methods

to identify customer feedback, reviews, opinions and

informative documents (Jansen, 2009, Ordenes et al.,

2014, Mankad et al., 2016). However, no study

presents the integration of diverse interactions among

several members of an ecosystem in a systematic

approach, either analyse the whole lifecycle

perspective of such interactions.

3 PROPOSED KNOWLEDGE

REQUIREMENTS

ELICITATION PROCESS

The elicitation process suggested in this paper

considers business related aspects, such as system

mapping, customer centricity and service lifecycle; as

well as technical related aspects, such as text data

mining analysis. The elicitation proposition adheres

to the service design process explained above,

focusing on the three first steps of it. The reason why

the elicitation process is developed in such way lies

in two arguments: (1) the need of practical studies that

consider a holistic approach of identifying, collecting

and analysing different data sources presented in a

service ecosystem and in each phase of service

lifecycle, and (2) the applicability of text data mining

tools to discover knowledge insights from non-

structured natural language sources. In industry, there

is a saturation of quantitative structured data with a

wide offer of technological and managerial

developments able to reach a high level of automation

in decision making.

The first step of the process consist in the use of

the system map tool proposed by Stickdorn et al.

(2018) in their collaborative service design approach

as a reference to present the relationships between

members of a product-service ecosystem. It

represents the value exchanges (money, goods,

services, and information) among such members. The

adaptations of the Stickdorn et al. (2018) system map

for our process consisted in solely two aspects. The

first one is the simplification of the value

representation. While the original map considers four

forms of value exchange, this proposed process only

contemplates the information exchanges and

interactions, since knowledge (information) is the

primary resource for creating smart services. The

second one is the integration of a lifecycle approach

into the system map. Namely, the process also maps

information exchanges and interactions between

ecosystem members through the whole service

lifecycle as shown in Figure 1.

Knowledge Requirements for Sustainable Smart Service Design

197

Figure 1: Service ecosystem value exchange (information)

mapping from a customer-centric and lifecycle approach

(adapted from (Stickdorn et al. 2018).

The purpose of the lifecycle approach is to give

deserving importance to the middle and last phases of

the lifecycle. In such a way, we cannot ignore the

environmental and social aspects, i.e., sustainability

issues. The system mapping is necessary at the

beginning to understand all the information

interactions between value partners in the ecosystem,

for later identify the data sources of such value

exchanges. In fact, the initial step of the process is to

identify and describe the sources of data collection

presented on every phase of the service lifecycle,

which can be presented in the form of text content,

reviews, interviews, brochures, flyers, reports and so

on. The further step consists of the data collection,

text data mining analysis and report of the analysis

results by presenting the most common and usual

Figure 2: Framework for determining Knowledge

Requirements for Sustainable Smart Service Design.

keywords obtained from such data sources. In the

particular case of our study, we decided to utilize the

data elements (sentiments, keywords, concepts,

categories, entities and text fragments) offered by

our text mining software enrichments. Data

enrichment is defined as an algorithm that process

unstructured text data from different sources to find

insights that were not referenced explicitly in the

text, interpreting the data into the context of other

information sources and simplifying the definitions

of specific topics (Hasan et al., 2011, IBM). A data

enrichment utilizes a linguistic approach which

considers the natural language contained in the data

sources, identifying the domain (topic) predominant

for effective analysis (Ordenes et al., 2014). The

data enrichment algorithm used by the software

employed in this study removes the irrelevant

elements and performs interdependency analysis to

bring the key or most relevant element set on the

members’ interaction. The elements that present a

higher co-occurrence are considered as knowledge

requirements. The whole requirement elicitation

process is illustrated in Figure 2.

4 CASE STUDY: OIL LUBRICANT

AND ADDITIVE

MANUFACTURER

ECOSYSTEM

An empirical study was used to apply and test the

elicitation process previously presented. The

members involved in the study were a car lubricant

and additive manufacturer and one of its main

customers, a fuel stations group providing full-

service offerings to its customers. The manufacturer

supplies several customers segments in its value

chain. Their customer segments are car workshops,

spare parts stores, retail stores, and its main

customer fuel stations. The fuel stations group

provide full-service offerings to its customers,

including gasoline and diesel filling, express car

washing and car liquid level checking, serving both

consumers and corporate clients. The optimal scope

of this study would be the full integration of all the

members involved in the manufacturer’s ecosystem.

However, due to the extension limitations of our

work, we will consider the system integrated by the

manufacturer and the service station group,

including its members and regulators, defined as the

micro-ecosystem.

KMIS 2019 - 11th International Conference on Knowledge Management and Information Systems

198

Figure 3: Service ecosystem value exchange (information)

mapping among members of case study.

The study began with two interviews made to the

Operations Managers from both companies. The

purpose of such meetings was to identify the data

sources presented in each interaction, considering the

whole service lifecycle. The members involved

within the manufacturers ‘side were sales

representatives, training leaders, technical

representatives and operations managers. From the

fuel stations group side, the members involved were

service operators, sales and operations managers.

Finally, the regulator´s side was represented by

governmental institutions and private quality

assurance entities. The value (information) exchanges

between members are graphically represented in the

system map shown in Figure 3.

The managers from both companies provided the

data sources resulting from the previously mentioned

interactions. As shown in figure 4, several data

sources were identified for the different members

interactions across the whole service lifecycle,

representing the first part of our elicitation process.

Diverse areas involving the performance, customer

feedbacks, safety issues and product handling were

found. According to our interviews and employees´

recommendations, we selectively categorized four

areas or fields for our analysis: Safety, Regulations,

Performance and Disposal. The next step was to

perform the text mining analysis. The software used

for this study was IBM Watson Discovery, a cloud-

based solution which uses algorithms to process text

data from diverse sources, transforming raw

unstructured data into explicit and implicit findings.

We proceed to upload all the text documents

previously into the software cloud in order to carry

out the text mining process and knowledge discovery.

After the text mining process was finished and data

enrichment analysis was performed, the software

brought us outputs composed of multiple key

elements. The chosen elements were selected based

on their co-occurrence, which are the elements with

Figure 4: Sources of data collection through the phases of service lifecycle.

Knowledge Requirements for Sustainable Smart Service Design

199

more interdependency with each other once the

software eliminates irrelevant elements and performs

the statistical analysis for term frequency. The last

one is an automate process that brings the most

common and used keywords presented in the

documents. As shown in Table 1, we organized the

key elements (outputs) presented according to the

areas previously described and the three phases of

service lifecycle as illustrated in Figure 4. Finally,

once the key element set is obtained and organized, it

is utilized as the main input to construct the whole

knowledge requirements elicitation process,

necessary for further smart service design process

steps, which are object of study for future research.

5 RESULTS AND DISCUSSION

In order to describe the results obtained and

illustrated in Table 1, the following lines will explain

the origin and application of the key elements

discovered, henceforth expressed as knowledge

requirements. We begin presenting the keywords

output brought by the statistical analysis for term

frequency, which is one of the previous analysis

before obtaining the key elements by co-occurrence

or interdependency. The most frequent terms by study

area are: (1) Safety keywords related to health

hazards and risks that the handling of lubricant and

additives can cause to human health, such as

Inhalation, Skin, Toxicity, Breathing and Irritation;

(2) Regulations keywords with strong emphasis on

the compliance and environmental preservation

fields, such as Pollution, Carbon Monoxide, Hazards,

and ISO and OSHA standards; (3) Performance

keywords aiming the knowledge of the recommended

product to use in each car and situation, such as

Application, Benefits, Applications, 100000 Km,

Transmission, Corrosion, Viscosity Index, Synthetic;

(4) Disposal keywords related to waste management

and handling of liquid and solid hazardous waste,

such as Residues, Collectors, Spills, Environment,

Containers, Lifecycle and Transportation.

As we can observe, the keywords brought by the

term frequency statistical analysis only provide single

words without any natural linguistic-based outcomes

involving the syntax, grammar and interdependency

of elements. The resulted keywords are important to

understand the repeatability in words an identify

certain parameters. However, the analysis concerned

to this study involves the more complex process

involved after the software eliminates irrelevant

elements and brings term frequency, the linguistics-

based co-occurrence analysis, which bring us key

data elements in form of composed keywords.

As shown in Table 1, we can identify several key

elements that illustrate the knowledge requirements

in a structured way after the co-occurrence analysis.

It reveals us the exact knowledge need presented in

each phase of the service lifecycle. Firstly, at the

Beginning of Life phase we can find elements related

to the information of the properties, characteristics

and classification and disposal of the product. It

interesting in this case that the main requirements are

not service concerned, rather product orientated.

Makes sense in the way fuel stations operators and

managers demand all the crucial knowledge needed

to perform an optimal service, keeping the customers

and employees in the safest condition before their

activities begin. Elements such as Toxicological

Information, Component Information, Oils and

Additives Classification and Uses, and Confined

Spaces confirm us the concerns. Currently,

employees do not have the technological tools to

extract the most important information from data

sources, given the fact that such information is

contained in hundreds of electronic or paper

documents in form of technical data sheets, safety

sheets, training presentations, and so on. Making the

request of single query a very challenging and time-

consuming task to be done. Therefore, even when

employees are constantly trained, some valuable

knowledge is still hidden within the document pages.

Secondly, at the Middle of Life phase we observe a

transition towards the performance of the service per

se. In the performance area, the elements of

Recommended Applications and Car Condition

Determination explain us the need of recognizing the

diverse conditions a car could face. As we previously

observed in the frequent keywords, information

regarding the condition of the transmission, high-

kilometrage engines, corrosion and many more car

states are concerns to determine the correct product

and service offering. However, nowadays service

providers are guided on their previous experience,

traditional training and colleague advise, guiding

them to offer a service susceptible to errors. In the

Safety and Regulations areas, we notice the interest to

preserve human integrity while providing the service.

The elements Security Practices, Risk Control

Procedures and Chemical Substance Practice are

related to the protocols the employees must follow in

order to mitigate risks and the way they respond to

possible emergencies when handling chemical

products in the service activities. In the Disposal area,

the elements of

Product Spills and Cleaning Methods

clearly describe the need to know the procedures in

KMIS 2019 - 11th International Conference on Knowledge Management and Information Systems

200

Table 1: Knowledge discovery of key data elements for requirements elicitation.

case the product leaks in certain surfaces when giving

the service, causing an environmental damage and

potential hazards. Finally, at the End of Life phase,

naturally the areas of Disposal and Regulations are

presented. The elements of Appropriate Containers,

Dangerous Residues and Waste Collection provide us

a convinced idea that the main knowledge

requirements are related to processes and regulations

in storage, transportation and confinement of residues

for sustainable and safety purposes.

6 CONCLUSIONS

The practical contribution of this paper is to bring us

an understanding of the main knowledge needs from

the people involved in the operational and customer

service processes every day. Which is one of the pillar

steps in the development of the smart worker or the

so-called Operator 4.0, also presented at service and

retail industries. Previous research mainly focuses on

the development of the smart worker within purely

manufacturing environments, without mentioning the

opportunities on their peripheric ecosystem members.

Two main novel tools contributed to the development

of the proposed process. First, the use of the system

mapping tool to understand the information value

flows and data sources needed, considering all the

phases of the service proposition and all the members

involved within the ecosystem. Second, the

application of text data mining from the data sources

allows us to comprehend the key elements presented

in different ecosystem process, identifying the

information or knowledge needs for the further smart

service design phases.

We identified three main limitations to our study

that can be tackled for future research. First, our

results depend on the analysis of the given data

sources documents from case companies. We infer

that the quality and amount of information contained

on the documents provided by the managers from the

two companies were adequate. However, the

information contained on the documents can change

overtime and the amount naturally will raise. That

could be an opportunity to address a more complex

analysis and better algorithm training. Second, the

study did not describe in detail each business process

involved within the ecosystem members. For general

purposes, this the scope of this study was appropriate.

However, future research may address the analysis of

business processes in a systematic way to

comprehend the pain points and needs involved.

Third, this study employed tool IBM Knowledge

Discovery for text data mining. Which is a software

with a high degree of process automation, making

easier to non-field experts in the data science area to

perform high-quality analyses. However, future

research could focus on providing more specialized

Fields BOL MOL EOL

Safety Hazard

Communication

Security Practices

Toxicological

Information

Risk Control

Procedures

Regulations Component

Information

Chemical Substance

Handling

Appropriate

Containers

Performance Product Classification

Recommended

Applications

Disposal

Product Uses Car Condition

Determination

Confined Spaces

Product Spills Dangerous Residues

Contractor

Competence

Cleaning Methods Waste Collection

Knowledge Requirements for Sustainable Smart Service Design

201

data analysis performed by experts as collaborators of

further works, who could exploit state-of-the-art

methods. Since the study involves both managerial,

business and technical work, it would be necessary to

achieve a collaborative and multidisciplinary

environment, integrated by field experts, operators,

managers, regulators, and other members presented in

the ecosystem.

REFERENCES

Antikainen, M. & Valkokari, K. 2016. A framework for

sustainable circular business model innovation, Techno-

logy Innovation Management Review, vol. 6, no. 7.

Bauer, C., Buchgeister, J., Hischier, R., Poganietz, W.R.,

Schebek, L. & Warsen, J. 2008. Towards a framework

for life cycle thinking in the assessment of

nanotechnology, Journal of Cleaner Production, vol.

16, no. 8-9, pp. 910-926.

Bird, S., Klein, E. & Loper, E. 2009. Natural language

processing with Python: analyzing text with the natural

language toolkit, " O'Reilly Media, Inc.".

Bitner, M.J., Ostrom, A.L. & Morgan, F.N. 2008. Service

blueprinting: a practical technique for service

innovation, California management review, vol. 50, no.

3, pp. 66-94.

Fayyad, U., Piatetsky-Shapiro, G. & Smyth, P. 1996. From

data mining to knowledge discovery in databases, AI

magazine, vol. 17, no. 3, pp. 37.

Hasan, S., Curry, E., Banduk, M. & O'Riain, S. 2011.

Toward situation awareness for the semantic sensor

web: Complex event processing with dynamic linked

data enrichment, Proceedings of the 4th International

Conference on Semantic Sensor Networks-Volume

839CEUR-WS. org, , pp. 69.

Hein, A., Scheiber, M., Böhm, M., Weking, J. & Krcmar,

H. 2018. Towards a design framework for service

platform ecosystems, 26th European Conference on

Information Systems. Portsmouth, United Kingdom.

Hsieh, H. 2005. Three approaches to qualitative content

analysis, Qualitative health research, vol. 15, no. 9, pp.

1277.

IBM, Data enrichment. Available: https://www.ibm.com/

watson/whitepaper/discovery/data-enrichment.html

[2019, "Mar 23, "].

Jansen, B.J. 2009. Twitter power: Tweets as electronic

word of mouth, Journal of the American Society for

Information Science and Technology, vol. 60, no. 11,

pp. 2169-2188.

Kim, M., Lim, C., Lee, C., Kim, K., Park, Y. & Choi, S.

2018. Approach to service design based on customer

behavior data: a case study on eco-driving service

design using bus drivers’ behavior data, Service

Business, vol. 12, no. 1, pp. 203-227.

Lempinen, H. & Rajala, R. 2014. Exploring multi-actor

value creation in IT service processes, Journal of

Information Technology, vol. 29, no. 2, pp. 170-185.

Lim, C., Kim, K., Kim, M., Heo, J., Kim, K. & Maglio, P.P.

2018. From data to value: A nine-factor framework for

data-based value creation in information-intensive

services, International Journal of Information

Management, vol. 39, pp. 121-135.

Lim, C., Kim, K., Kim, M. & Kim, K. 2018. Multi-factor

service design: identification and consideration of

multiple factors of the service in its design process,

Service Business, pp. 1-24.

Lim, C. & Maglio, P.P. 2018. Data-driven understanding of

smart service systems through text mining, Service

Science, vol. 10, no. 2, pp. 154-180.

Lüftenegger, E., Comuzzi, M. & Grefen, P.W. 2017.

Designing a tool for service-dominant strategies using

action design research, Service Business, vol. 11, no. 1,

pp. 161-189.

Lusch, R.F. & Nambisan, S. 2015. Service innovation: A

service-dominant logic perspective, MIS quarterly, vol.

39, no. 1.

Lusch, R.F. & Vargo, S.L. 2014. Evolving to a new

dominant logic for marketing in The Service-Dominant

Logic of Marketing Routledge, , pp. 21-46.

Lusch, R.F., Vargo, S.L. & Gustafsson, A. 2016. Fostering

a trans-disciplinary perspectives of service ecosystems,

Journal of Business Research, vol. 69, no. 8, pp. 2957-

2963.

Macdonald, E. 2011. Assessing value-in-use: A conceptual

framework and exploratory study, Industrial Marketing

Management, vol. 40, no. 5, pp. 671.

Mankad, S., Han, H., Goh, J. & Gavirneni, S. 2016.

Understanding online hotel reviews through automated

text analysis, Service Science, vol. 8, no. 2, pp. 124-138.

Mikroyannidis, A. 2006, Heraclitus II: A Framework for

Ontology Management and Evolution.

Neuhüttler, J., Woyke, I., Ganz, W. & Spath, D. 2018. An

Approach for a Quality-Based Test of Industrial Smart

Service Concepts, International Conference on Applied

Human Factors and ErgonomicsSpringer, , pp. 171.

Ordenes, F., Burton, J., Theodoulidis, B., Gruber, T. &

Zaki, M. 2014. Analyzing customer experience

feedback using text mining: A linguistics-based

approach, Journal of Service Research, vol. 17, no. 3,

pp. 278-295.

Orellano, M., Lambey-Checchin, C., Medini, K. & Neubert,

G. 2018. Towards an integration of lifecycle thinking

into PSS business models, Procedia CIRP, vol. 73, pp.

291-296.

Stickdorn, M., Hormess, M.E., Lawrence, A. & Schneider,

J. 2018. This Is Service Design Doing: Applying Service

Design Thinking in the Real World, "O'Reilly Media,

Inc.".

Vargo, S.L. & Lusch, R.F. 2011. It's all B2B… and beyond:

Toward a systems perspective of the market, Industrial

marketing management, vol. 40, no. 2, pp. 181-187.

Yu, C.H. 2011, "Compatibility between Text Mining and

Qualitative Research in the Perspectives of Grounded

Theory, Content Analysis, and Reliability", Qualitative

Report, vol. 16, no. 3, pp. 730-744.

KMIS 2019 - 11th International Conference on Knowledge Management and Information Systems

202