Creation of unstructured big data from customer service. The case of parcel shipping companies on Twitter

• DOI: https://doi.org/10.1108/IJLM-06-2017-0157
• Published date: 14 May 2018
• Pages: 723-738
• Date: 14 May 2018
• Author: Jyotirmoyee Bhattacharjya,Adrian Bachman Ellison,Vincent Pang,Arda Gezdur
• Subject Matter: Management science & operations,Logistics

Creation of unstructured big data

from customer service

The case of parcel shipping companies

on Twitter

Jyotirmoyee Bhattacharjya and Adrian Bachman Ellison

Institute of Transport and Logistics Studies, The University of Sydney,

Sydney, Australia

Vincent Pang

School of Information Systems, University of New South Wales, Kensington,

Australia, and

Arda Gezdur

Institute of Transport and Logistics Studies, The University of Sydney,

Sydney, Australia

Abstract

Purpose –Customer service prov ision is a growing phenomen on on social media and parce l shipping

companies have been amo ng the most prominent adopters. This ha s coincided with greater interest in t he

development of analys is techniques for uns tructured big data fro m social media platfo rms, such as the

micro-blogging plat form, Twitter. Given t he growing use of dedi cated customer servi ce accounts on

Twitter, the purpose o f this paper is to investigate the ef fectiveness with which parcel shi pping companies

use the platform.

Design/methodology/approach –This paper demonstrates the use of a combination of tools for retrieving,

processing and analysing large volumes of customer service-related conversations generated between parcel

shipping companies and their customers in Australia, UK and the USA. Extant studies using data from

Twitter tend to focus on the contributions of individual entities and are unable to capture the insights

provided by a holistic examination of the interactions.

Findings –This study identifies the key issues that trigger customer contact with parcel shipping companies

on Twitter. It identifies similarities and differences in the approaches that these companies bring to customer

engagement and identifies the opportunities for using the medium more effectively.

Originality/value –The development of consumer-centric supply chains and relevant theories require

researchers and practitioners to have the ability to include insights from growing quantities of unstructured

data gathered from consumer engagement. This study makes a methodological contribution by

demonstrating the use of a set of tools to gather insight from a large volume of conversations on a social

media platform.

Keywords Europe, North America, Twitter, Customer service, Logistics services, Retail logistics,

Unstructured big data, Media richness, E-logistics, Global logistics, Big social data, Parcel shipping

Paper type Research paper

Introduction

The speed of generation of large volumes of data from business operations and the wide

variety of sources for such data (e.g. customer transactions, social media updates, GPS

signals from mobile phones) have led to the recognition of both opportunities and challenges

for managerial decision makers (Goes, 2014; McAfee and Brynjolfsson, 2012). Big data

analytics involves working with high volume and high velocity data from a range of

different sources (Richey et al., 2016) to increase operational visibility, identify performance

variabilities, tailor products and services to market segments, support business model

innovation and achieve competitive advantage in dynamic business environments (McAfee

and Brynjolfsson, 2012; Wamba et al., 2015; Wang et al., 2016). Big data can be of different

The International Journal of

Logistics Management

Vol. 29 No. 2, 2018

pp. 723-738

© Emerald PublishingLimited

0957-4093

DOI 10.1108/IJLM-06-2017-0157

Received 18 June 2017

Revised 13 November 2017

3 December 2017

Accepted 3 December 2017

The current issue and full text archive of this journal is available on Emerald Insight at:

www.emeraldinsight.com/0957-4093.htm

723

Creation of

unstructured

big data

types: structured, semi-structured and unstructured (Gandomi and Haider, 2015; Sagiroglu

and Sinanc, 2013). While much of the extant literature focusses on structured data, the

volume of unstructured data around the world is growing considerably more rapidly than

the structured data (Schneider, 2016).

Social media platforms including blogs, micro-blogging sites, wikis, social networking

and video sharing sites and virtual worlds have played a significant role in the growth of

high volume and high velocity unstructured data in a variety of contexts (Kaplan and

Haenlein, 2010). The rapid adoption of such platforms by end consumers has led managers

to recognise new engagement and promotion opportunities for their businesses (Kiron et al.,

2012). Companies have increasingly started connecting with customers using Facebook,

Twitter and blogs, and the provision of links between company websites and social media

sites has become part of the norm (Culnan et al., 2010; Gunton and Davis, 2012). This

phenomenon is driven by the potential for creating virtual customer communities that can

support branding, product development and sales (e.g. Jansen et al., 2009).

This study is conducted using data from the micro-blogging site, Twitter, which has over

320 million individual and organisational users around the world (Statista, 2017). The

platform is used for information dissemination by government agencies (Waters and

Williams, 2011), institutions of higher education (Linvill et al., 2012) and not-for-profit

organisations (Waters and Jamal, 2011). It has served as an important communication tool

during natural disasters (Drake, 2013; Papadopoulos et al., 2017). Businesses and

professionals use the platform for a range of different purposes including the introduction of

new products (Abney et al., 2017), sales improvement (Miller, 2009), responses to service

failures (Fan and Niu, 2016) and the reporting of breaking news (Vis, 2012). The platform

enables e-retailers to engage with a globally distributed consumer base (Bhattacharjya et al.,

2016). Since parcel shipping companies play an important role in the supply chains of these

e-retailers, the big data generated from the interactions of these carriers with end consumers

on Twitter could be useful in generating service quality-related insights for both partners.

Literature review

Big data in business operations and logistics

Recent evidence from research on big data analytics in operations and supply chain

management suggests that while shortage of relevant skills and managerial inertia continue

to pose challenges, big data analytics can provide significant benefits to businesses and

create lasting competitive advantage (Arya et al., 2017; Dutta and Bose, 2015; Matthias et al.,

2017; Richey et al., 2016). Big data sources may be harnessed for predictive analytics

(Ilie-Zudor et al., 2015; Waller and Fawcett, 2013) to provide insights for a number of supply

chain management challenges including predictive facility layout optimisation,

identification of qualitative and quantitative criteria related to suppliers and preferred

supplier and carrier selection (Lamba and Singh, 2017).

Unstructured big data from social media

The fastest growing type of big data around the world is unstructured and available in text,

audio, video and image formats (Gandomi and Haider, 2015). Social media platforms host

large volumes of unstructured big data created from the consumer engagement and brand

management activities of many companies (Aral et al., 2013) and have the potential for

producing significant insights for both practice and research in supply chain management

(Chae, 2015). Many companies are increasingly using the micro-blogging platform, Twitter,

for providing customer service (Gunton and Davis, 2012). E-retailers and e-commerce

companies have established customer service accounts on Twitter to address the concerns

of their customers (Bhattacharjya et al., 2016; Bhattacharjya and Ellison, 2015). Parcel

724

IJLM

29,2