Exploring the knowledge spillovers of a technology in an entrepreneurial ecosystem—The case of artificial intelligence in Sydney

• Author: Dilek Cetindamar,Thorsten Lammers,Yi Zhang
• Date: 01 September 2020
• Published date: 01 September 2020
• DOI: http://doi.org/10.1002/tie.22158

RESEARCH ARTICLE

Exploring the knowledge spillovers of a technology

in an entrepreneurial ecosystem—The case of artificial

intelligence in Sydney

Dilek Cetindamar | Thorsten Lammers | Yi Zhang

School of Information, Systems and Modelling,

Faculty of Engineering and IT, University of

Technology Sydney, Ultimo, New South

Wales, Australia

Correspondence

Dilek Cetindamar, School of Information,

Systems and Modelling, Faculty of Engineering

and IT, University of Technology Sydney,

15 Broadway, Ultimo, NSW 2007, Australia.

Email: dilek.cetindamarkozanoglu@uts.edu.au

Abstract

New knowledge presents opportunities for commercial value and can hence be a crit-

ical asset for entrepreneurial ecosystems (EEs). In particular, general purpose technol-

ogies are major drivers of entrepreneurship. Thus, a nuanced understanding on

technological knowledge and its spillovers among actors within an EE is warranted.

Using knowledge-spillover-based strategic entrepreneurship theory, we propose to

observe knowledge spillovers through the assessment of the knowledge bases of a

technology in an EE. To do so, this article proposes to use three key sources of

knowledge: publications reflecting the emerging knowledge base, patents rep-

resenting the realized knowledge base, and startups showing the experimental

knowledge base. This article uses secondary data sources such as Web of Science

and applies the method of bibliometrics to illustrate how an assessment is carried out

in practice by evaluating the artificial intelligence (AI) knowledge bases in Sydney

from 2000 to 2018. The findings are summarized with an illustration of the evolution

of the key actors and their activities over time in order to indicate the key strengths

and weaknesses in Sydney's AI knowledge among the different bases. Contrary to

expectations from the high potential of knowledge spillovers from a general purpose

digital technology such as AI, the article shows that apparent knowledge spillovers

are yet highly limited in Sydney. Even though Sydney has a strong emerging knowl-

edge base, the realized knowledge base seems weak and the experimental knowledge

base is slowly improving. That observation itself verifies the need to take strategic

actions to facilitate knowledge spillovers within EEs. After the implications for theory

and policy makers are discussed, suggestions for further studies are proposed.

KEYWORDS

artificial intelligence, entrepreneurial ecosystems, knowledge base, knowledge spillover,

Sydney, technical knowledge base

1|INTRODUCTION

Increasingly, research focuses on the relationship between knowledge

spillovers and an entrepreneurial ecosystem (EE), in which a commu-

nity of interdependent actors in a specific geographical region

generates entrepreneurial activities (Acs & Sanders, 2012; Heim,

Kalyuzhnova, Li, & Liu, 2019; Qian, 2017, 2018; Scaringella &

Radziwon, 2018; Subramaniam, Iyer, & Venkatraman, 2019). How-

ever, the literature on these spillovers and their impact on EEs is in its

early stages, as indicated in recent studies (Lindholm-Dahlstrand,

DOI: 10.1002/tie.22158

Thunderbird Int. Bus. Rev.. 2020;62:457–474. wileyonlinelibrary.com/journal/tie © 2020 Wiley Periodicals LLC. 457

Andersson, & Carlsson, 2019; Qian, 2018). Because knowledge spill-

over does not happen automatically (Qian & Jung, 2017), Ferreira,

Ratten, and Dana (2017) invite academicians and policy makers to be

proactive and use knowledge spillovers for strategic purposes in order

to generate innovative, risk taking, proactive, and competitive busi-

ness approaches. Their theory is called knowledge-spillover-based

strategic entrepreneurship (Ferreira et al., 2017) and this article

adopts it in order to explore the relationship between knowledge spill-

overs and EEs. In particular, the article argues that understanding

knowledge bases within an ecosystem could help actors in EEs to

develop strategic decisions regarding deliberate actions to improve

knowledge spillovers among themselves. That is why this article aims

to focus on the assessment of the knowledge bases for a given tech-

nology within an EE in order to improve their commercial exploitation

within its context.

The development of human knowledge is geographically embed-

ded: social, economic, cultural, and cognitive environments influence

social interactions and human capital (Alvedalen & Boschma, 2017;

Caragliu, Bo, & Nijkamp, 2011; Marshall, 1898). The unit of geographi-

cal analysis might be a city, region, or country, but recent studies that

examine knowledge spillovers or EEs increasingly prefer cities or met-

ropolitan areas (Autio, Nambisan, Thomas, & Wright, 2018;

Cetindamar & Gunsel, 2012; Cetindamar, Lammers, & Sick, 2019;

Groth, Esposito, & Tse, 2015; Newman, 2017; Qian, 2018). There are

also many indexes that rank cities across countries on the basis of dig-

ital technology or entrepreneurial activity (European Digital

Forum, 2016). For example, the Global Startup Ecosystem Report

ranks 150 cities around the globe according to their entrepreneurial

performance (Global Startup, 2019).

To join the stream of studies that investigate the dynamics of a

knowledge base within an EE (Helfat & Raubitschek, 2018;

Qian, 2018), this article proposes an assessment approach to evaluate

the technical knowledge bases for a technology in a city and then

implements it in a real-life example. Most studies in this area use the

two key metrics of publications and patent databases to measure the

technical knowledge present in a region (Acs, Braunerhjelm,

Audretsch, & Carlsson, 2009; Acs & Sanders, 2012; Börner, 2014).

Bringing the knowledge-spillover theory of entrepreneurship (Ferreira

et al., 2017; Qian, 2018) to bear, this article considers startup activity

as a third metric for such assessments.

As an empirical illustration of this type of assessment, this article

analyzes the knowledge bases of the general purpose digital technol-

ogy called artificial intelligence (AI), which has the potential to change

all aspects of production, consumption, and government services in

daily life (Schwab, 2016). In addition, unlike many other digital tech-

nologies, such as robots, AI represents the invention of a method of

inventing, in that it can be used to invent new applications of technol-

ogy, such as autonomous driving and condition-based maintenance,

or develop new pharmaceuticals (Cockburn, Henderson, &

Stern, 2019). Due to its wide range of potential opportunities, AI is

expected to have a massive impact on EEs (Groopman, Lieb,

Owyang, & Szymanski, 2017). In the regional context, this article uses

the city of Sydney as a rich EE because it is the site of Australia's

highest concentration of technology startups, home to almost half of

them, and with 20% of them researching, developing, or selling in the

area of AI (Startup Muster, 2018).

This article has four more sections. Section 2 introduces a sum-

mary of the EE concept, followed by a section presenting the relation-

ships between knowledge bases, knowledge spillovers and EEs.

Section 4 summarizes the methodology of the article. Section 5 pre-

sents the findings related to the three knowledge sources of publica-

tions, patents and startups/entrepreneurial activities. The last

section summarizes the results of the article and ends with sugges-

tions for future research.

2|ENTREPRENEURIAL ECOSYSTEMS

Ecosystem is a commonly used concept in biology and expresses the

common life of different species in a certain environment. The bound-

aries may or may not be physical, but in any case, they determine the

inputs and outputs of the system and thus create an independent life

within the ecosystem. There are critical resources in the ecosystem

and actors that influence the use of these resources. In other words,

the ecosystem is a collaboration involving dynamic interactions

between the actors' interdependence in a given environment

(Adner, 2017; Sussan & Acs, 2017).

The concept of ecosystem in business literature begins with the

work of Moore (1993). According to Moore, the business ecosystem

refers to the co-existence and close relationship of different types of

firms, universities and many other corporate structures / actors in a

geographically defined common environment. According to the most

widely used definition, an EE is “a set of interconnected entrepreneur-

ial actors (both potential and present), entrepreneurial organizations

(e.g. firms, venture capitalists, business angels, banks), institutions

(universities, commercial agencies, financial institutions) and coopera-

tion between them”(Mason & Brown, 2014, p. 5).

In this article, an EE is treated as a system in which all actors and

the relationships between them are effective from the formation of

opportunities to the implementation of these opportunities (Aarikka-

Stenroos & Rittala, 2017; Van der Borgh, Cloodt, & Romme, 2012).

EEs might substantiate in various forms. For example, there are flexi-

ble EEs in which relations between members or stakeholders of the

ecosystem are ambiguously defined, and EEs with strict rules and

where all relationships are defined (Clarysse, Wright, Bruneel, &

Mahajan, 2014). The best example of an inelastic EE is the “platform

ecosystem”(Gawer & Cusumano, 2014). There is a main actor in this

ecosystem; all other ecosystem members develop complementary

products, services or technologies as part of the platform established

by this actor. The most extreme example of a flexible EE is an “open

innovation”ecosystem defined by spontaneous, independent actions,

ultimately contributing to the development of a common innovation

(Chesbrough, Sohyeong, & Agogino, 2014; Eckhardt, Ciuchta, &

Carpenter, 2018).

In the last 10 years, the studies on EEs have increased greatly.

Recent studies present detailed accounts of literature reviews and

458 CETINDAMAR ET AL.