Call Center Operators Research Articles

Introduction to the Special Issue on Data Mining of Speech, Audio, and Dialog

ATA mining is concerned with the science, technology, and engineering of discovering patterns and extracting potentially useful or interesting information automatically or semi-automatically from data. Data mining was introduced in the 1990s and has deep roots in the fields of statistics, artificial intelligence, and machine learning. With the advent of inexpensive storage space and faster processing over the past decade or so, data mining research has started to penetrate new grounds in areas of speech and audio processing as well as spoken language dialog. It has been fueled by the influx of audio data that are becoming more widely available from a variety of multimedia sources including webcasts, conversations, music, meetings, voice messages, lectures, television, and radio. Algorithmic advances in automatic speech recognition have also been a major, enabling technology behind the growth in data mining. Current state-of-the-art, large-vocabulary, continuous speech recognizers are now trained on a record amount of data—several hundreds of millions of words and thousands of hours of speech. Pioneering research in robust speech processing, large-scale discriminative training, finite state automata, and statistical hidden Markov modeling have resulted in real-time recognizers that are able to transcribe spontaneous speech with a word accuracy exceeding 85%. With this level of accuracy, the technology is now highly attractive for a variety of speech mining applications. Speech mining research includes many ways of applying machine learning, speech processing, and language processing algorithms to benefit and serve commercial applications. It also raises and addresses several new and interesting fundamental research challenges in the areas of prediction, search, explanation, learning, and language understanding. These basic challenges are becoming increasingly important in revolutionizing business processes by providing essential sales and marketing information about services, customers, and product offerings. They are also enabling a new class of learning systems to be created that can infer knowledge and trends automatically from data, analyze and report application performance, and adapt and improve over time with minimal or zero human involvement. Effective techniques for mining speech, audio, and dialog data can impact numerous business and government applications. The technology for monitoring conversational speech to discover patterns, capture useful trends, and generate alarms is essential for intelligence and law enforcement organizations as well as for enhancing call center operation. It is useful for an

Nurses to be among the ‘rarest of species’ by 2010

Nursing shortages are set to worsen over the next 15 years, with only vacancies for call centre operators and science technicians harder to fill by 2020, it has been claimed.

The Power of Non-Verbal Communication: Predicting Job Performance by Means of Thin Slices of Non-Verbal Behaviour

The purpose of the study was to investigate whether ratings of brief exposures to ‘non-verbal’ and ‘non-verbal plus verbal’ behaviour could successfully predict on-the-job performance in a call centre. A panel often judges who were exposed to 30-second silent video recordings of 29 call centre operators carrying out their jobs were asked to rate the non-verbal behaviour of the operators on several dimensions. Two weeks later they were asked to repeat their judgments with the audio channel included. The judgments were correlated with management ratings and customer ratings of the operators' performance. The correlations varied between 0.31 and 0.46, representing medium to large effect sizes. The inclusion of the verbal channel did not significantly improve the accuracy of the thin-slice judgments of non-verbal behaviour. The implications of using ratings of non-verbal behaviour as a selection method were discussed.

Statistical Analysis of a Telephone Call Center

A call center is a service network in which agents provide telephone-based services. Customers who seek these services are delayed in tele-queues. This article summarizes an analysis of a unique record of call center operations. The data comprise a complete operational history of a small banking call center, call by call, over a full year. Taking the perspective of queueing theory, we decompose the service process into three fundamental components: arrivals, customer patience, and service durations. Each component involves different basic mathematical structures and requires a different style of statistical analysis. Some of the key empirical results are sketched, along with descriptions of the varied techniques required. Several statistical techniques are developed for analysis of the basic components. One of these techniques is a test that a point process is a Poisson process. Another involves estimation of the mean function in a nonparametric regression with lognormal errors. A new graphical technique is introduced for nonparametric hazard rate estimation with censored data. Models are developed and implemented for forecasting of Poisson arrival rates. Finally, the article surveys how the characteristics deduced from the statistical analyses form the building blocks for theoretically interesting and practically useful mathematical models for call center operations.

Risk Factors for Musculoskeletal Symptoms among Call Center Operators of a Bank in Sao Paulo, Brazil

Identify risk factors for musculoskeletal symptoms among call center operators of a bank in São Paulo, Brazil. Ergonomic work analysis was carried out, involving work observation and interviews. Self-answered questionnaires performed by 108 call center operators. Women represented 88% of the call center operators, 70% of them were in the age bracket of 18 to 23 yr. Daily working time was 6-h with one 30 min break. Workers remained seated 95% of the time, typing and answering telephone calls. Men' s work consisted of more active telemarketing and women's of customer services. Among female operators the prevalence of neck/shoulder symptoms was 43% (95% CI, 33-53) and of wrist/hand was 39% (95% CI, 29-49). Risk factors associated with wrist/hand symptoms were: inadequate height of table (Odds ratio (OR) 3.67, 95% CI, 1.12-11.96) and to answer above 140 calls/d (OR 3.36, 95% CI, 1.16-9.71). Risk factors associated with neck/shoulder symptoms were making fewer rest breaks (OR 3.17, 95% CI, 1.11-8.97) and inadequate thermal comfort (OR 3.06, 95% CI, 1.09-8.62). Prevention of musculoskeletal disorders among call center operators requires an integrated approach including improved workstation design, thermal comfort environment, well-scheduled work-rest regime and realistic production goals.

Modelling and analysis of e-mail management for improved customer relationship management

Customer contact centres represent a growing industry in which Customer Relationship Management (CRM) applications have been developed and used successfully. Customer call centres, a multi-billion dollar industry, are evolving into customer contact centres, which now include channels of communication other than the telephone. E-mail, a popular alternative to the telephone for all types of communication, is becoming a common medium for customer contact. CRM applications currently exist that allow us to implement and monitor e-mail management strategies. For example, incoming e-mail can be automatically routed to specific customer service agents according to predefined routing rules. The routing mechanisms available in the software tools are heuristic, and not based upon any scientific analysis of the performance of different routing policy alternatives. The objective of this paper is to study the impact of routing strategies and prioritisation of incoming e-mail messages on CRM objectives of an organisation. We create a model representative of and consistent with e-mail response centres in industry. The process modelled was corroborated by a domain expert. A comprehensive simulation study is conducted to analyse different routing policies and prioritisation options. The results of the simulation study indicate that specific routing strategies and the use of specific priority schemes by the e-mail agent can result in a significant improvement in the response centre's performance, as indicated by average response times and average resolution times of different categories of e-mail messages. Although call centre operations have been studied extensively, this study shows that performance of contact centres needs further investigation because of the greater flexibility that exists in the assignment and scheduling of e-mail processing tasks.

La geographie des centres d'appels en France//The French geography of the call-center industry

Les centres d'appels constituent une des activités émergentes de la nouvelle économie. Ils proposent au geographe une problématique intéressante: quels sont les facteurs de localisation d'établissements qui délivrent au client un service à distance. La carte des implantations dans les aires urbaines franchises, comptabilisées par postes de travail, montre une répartition spatiale irrégulière, mais qui reste fortement metropolisés. Une analyse plus fine met en evidence un processus de diffusion hiérarchique, à partir de la Capitale, puis vers les métropoles régionales, et enfin vers I'espace à dominante rurale. Ce processus crée des opportunités de créations d'emploi. Les centres d'appels sont devenus la cible des politiques locales de développement économique, et un outil de reconversion des bassins d'emploi en difficulté. Mais la croissance des délocalisations outre-mer fait peser une menace sur ces activités nouvelles. La croissance des centres d'appels est un des phénomènes par lesquels les territoires entrent dans l'ère du «capitalisme cognitif», dans un contexte de globalisation et de métropolisation. Mais les effets dynamisants de cette activité fortement taylorienne sont incertains, et elle ne saurait en aucun cas devenir une mono-activité.

The performance and subjective responses of call-center operators with new and used supply air filters at two outdoor air supply rates

A 2 x 2 replicated field intervention experiment was conducted in a call-center providing a telephone directory service: outdoor air supply rate was adjusted to be 8% or 80% of the total airflow of 430 l/s (3.5 /h) and the supply air filters were either new or had been in place for 6 months. One of these independent variables was changed each week for 8 weeks. The interventions did not affect room temperature, relative humidity or noise level. The 26 operators were blind to conditions and each week returned questionnaires recording their environmental perceptions and Sick Building Syndrome (SBS) symptoms. Their performance was continuously monitored by recording the average talk-time every 30 min. Replacing a used filter with a clean filter reduced talk-time by about 10% at the high ventilation rate but had no significant effect at the low rate. Increasing the outdoor air supply rate reduced talk-time by 6% with a new filter in place but increased talk-time by 8% with a used filter in place. The interventions also had significant effects on some SBS symptoms and environmental perceptions. The present results indicate that increasing outdoor air supply rate and replacing filters can have positive effects on health, comfort and performance. Supply air filters should be changed frequently not just because their airflow resistance increases progressively but because they degrade air quality with negative consequences for health, comfort and the performance of office work, all of which are factors that affect office productivity (profitability). Increasing outdoor air supply rates may only be beneficial when new filters are installed. Unwanted negative effects may be produced when used filters are in place. Filter condition (used or new) should always be recorded to make it possible to draw sound conclusions in studies of the effects of outdoor air supply rates on building occupants.

‘We have the values’: customers, control and corporate ideology in call centre operations

This article analyses the use of normative control through recruitment, work organisation, social events, and bargaining processes within two Australian telecommunication call centres. Rather than arguing that such control reduced employees to ‘self‐disciplining subjects’, it suggests that these control mechanisms embodied significant levels of managerial coercion and therefore attracted varying levels of resistance.

What is typical for call centre jobs? Job characteristics, and service interactions in different call centres

Call centres have been one of the few booming branches in recent years. The main task of call centre operators is to interact with customers by telephone, usually supported by computer systems. It has been argued that call centre work is a modern form of “Taylorism”, because it is characterized by routine tasks, and low level of control for the employees. Moreover, it has been suggested that there is a high level of stress at work, both with regard to the work tasks and to the interactions with customers. In the present study a sample of 375 call centre employees from eight different call centres was compared with a sample of noncall centre workers (N = 405) in terms of job characteristics, job stressors, and emotional labour (emotion work). The results showed that call centre workers had worse job characteristics, but were better off with regard to most job stressors compared to representative comparison groups of no-service workers, service workers, and workers in human services respectively. Moreover, compared to the other groups, customer service representatives (CSRs) had to express less negative emotions, but were most frequently exposed to states of emotional dissonance. A comparison of the working conditions of the eight call centres revealed that in most call centres the working conditions could be substantially improved. In addition, various call centre parameters such as inbound vs. outbound, or inhouse vs. external service centres were examined. The strongest effects were found for the percentage of time spent on the telephone. With some exceptions, the results support the view that the majority of call centres have been established to organize mass service for customers, that the work in the call centres is characterized by routine work and low task control, and that call centre employees are required to suggest a “friendly smile” when they are on the phone.

All Talk But No Voice: Employee Voice at the Eurotunnel Call Centre

There is little existing research on non-union voice structures of consultation and representation in call centres, or on the impact and influence of such structures on either organizational change or employee influence over managerial decisions. This article attempts to address these issues by examining non-union consultation and representative arrangements at the call centre operations at Eurotunnel, and assessing their effectiveness in representing the needs of employees. Overall, the evidence suggests that the non-union voice structures at the Eurotunnel call centre are used as devices for information and communication rather than true consultation mechanisms or bargaining agents; their effectiveness as bodies representing the interests of call centre employees in filling the lack of representation is questionable. The implications for organizations of not recognizing such limitations of non-union arrangements could result in increased union influence on workplace issues and greater employee dissatisfaction with management. The study concludes that communication between management and employees at the workplace may not be enough: voice and the right to be heard may be essential for achieving higher performance and employee commitment.

Perceptions and experience of workplace bullying in five different working populations

AbstractWhilst aggression in the workplace has been systematically studied in recent years, research into workplace bullying per se still remains quite limited. In this article, we report the findings from an investigation into employees' perceptions of social and organizational work conditions and experiences of bullying at work. Six‐hundred‐seventy‐seven employees from five different working populations (managers, teachers, technicians, call centre operators, and engineers) completed the Workplace Relationships Questionnaire (WRQ). This paper presents the results of the analysis, linking the experiences of bullying and perceptions of social and organizational work conditions. The present findings predictably identify victims and non‐bullied participants, and also indicate the existence of a new category of employee affected by the problem of bullying; bullied/non‐victims. Bullied/non‐victims may provide crucial insights into the ways that company practices and policies impact negatively on the whole workforce. Aggr. Behav. 29:489–496, 2003. © 2003 Wiley‐Liss, Inc.

Services innovation and the transformation of work: the case of UK telecommunications

Current transformations in technologies and industrial structure of UK telecommunications have important implications for skills and work organisation. This is examined in different divisions of a large UK telecommunications firm: call centres, customer service centres, engineering sectors and the R&D department. The effect of these transformations on the development of firm competences is discussed.

The Talk Shop and Shop Talk: Employment and Work in a Call Centre

Call centres represent a blend of old and new employment features that are only partially grasped by existing theoretical alternatives.Labour process theory suggests that call centres are best depicted as new electronic assembly lines of fragmented, low skill service labour. Second–wave post–industrial theory represents call centres as a signi?cant foray into the information/knowledge economy. On the basis of a case study that combines both survey results and on–site observation, the author argues that the sophisticated information technologies that have captured the awe of other investigators have delivered less than total managerial control.Less frequently studied are the novel cultures of employment management that have accompanied the development of call centres and have incorporated information technology into their functioning. These cultures and employee responses to them represent an important, if under–analysed, aspect of call centre operation.

Assessment of the noise exposure of call centre operators.

Call centres now play a major role in the daily operations of financial, technology and utility companies, as well as public bodies. It is predicted that 2002 will see 2.3% of the total British workforce employed in call centres. However, local authority enforcement officers, unions, voluntary organizations, employers and employees have all expressed concern that there are hazards to health and safety unique to this new and developing industry. One of the potential hazards reported in the press is hearing damage from using headsets. In a Health & Safety Executive funded project, the noise exposure of 150 call centre operators was evaluated, in call centres which included financial services, home shopping and telecommunications services. The results show that the daily personal noise exposure of these call centre operators is unlikely to exceed the 85 dB(A) action level defined in the Noise at Work Regulations 1989. The risk of hearing damage is therefore extremely low. Exposure to higher noise levels is possible, for example from fax tones, holding tones and high pitched tones from mobile phones. However, the duration of these events is likely to be short and they are therefore unlikely to have a significant effect on the operators' overall noise exposure. A practical method of limiting exposure to unexpected high noises from headsets is to ensure that the headsets incorporate acoustic shock protection that meets the requirements of the Department of Trade and Industry specification 85/013. In the UK, this limiter ensures any noise above 118 dB is not transmitted through the headset. Operators should receive regular training on the headset and telephone equipment they are using. This training should include correct use of the headset and the volume control facilities, and advice on how and when to clean and maintain the headsets.

Information systems at CallCentre

This paper presents the latest empirical material to emerge from a recently completed research project using the organisational scenario tool (OST). The project was part of a large-scale activity conducted over a 3-year period and was funded by the EPSRC under their Software Engineering for Business Process Change programme. The project has been looking at legacy systems and evaluating their potential for change. The methods adopted here are based on scenario generation and include an iterative process that attempts to ‘future proof’ organisational options for change. The empirical research presented in this paper took place within a large UK-based company that is structured around a call centre operation (referred to hereafter as CallCentre). The research focused on a particular job management function of the business (referred to as Works). Major problems were being encountered with the flow of work through the business process chain. CallCentre made it clear that the technology involved was inadequate to support the complexity and size of the tasks being performed. However, one of the main conclusions of this paper is that what appeared on the surface to be an information systems problem turned out to be much more to do with a need for change in work organisation and organisational attitude. Although at one level this challenged management expectations, it also had positive outcomes for the business. The OST demonstrated its effectiveness in highlighting the assumptions underpinning different technological and organisational choices at CallCentre and was able to assist the organisation in its decision-making process. At the same time the framework provided a valuable archive ensuring that the organisation could revisit these decisions at a later date with the benefit of hindsight.

A Data-Driven Methodology for Evaluating and Optimizing Call Center IVRs

Usability of many call center IVRs (Interactive Voice Response systems) is dismal. Callers dislike touch-tone IVRs and seek agent assistance at the first opportunity. However, because of high agent costs, call center managers continue to seek automation with IVRs. The challenge for call centers is providing user-friendly, yet cost-efficient, customer service. This article describes a comprehensive methodology for usability re-engineering of telephone voice user interfaces based on detailed call center assessment and call flow redesign. At the core of our methodology is a data-driven IVR assessment, in which we analyze end-to-end recordings of thousands of calls to evaluate IVR cost effectiveness and usability. Because agent time is the major cost driver in call center operations, we quantify cost-effectiveness in terms of agent time saved by automation in the IVR. We identify usability problems by carefully inspecting user-path diagrams, a visual representation of the sequence of events of thousands of calls as they flow through the IVR. Such an IVR assessment leads directly into call-flow redesign. Assessment insights lead to specific suggestions on how to improve a call-flow design. In addition, the assessment enables us to estimate the cost savings of a new design, thus providing the necessary business justification. We illustrate our IVR usability and re-engineering methodology with examples from large commercial call centers, demonstrating how the staged process maximizes the payback for the call center while minimizing risk.

Monitoring And Surveillance In Call Centres: Some Responses From Australian Workers

The call centre industry has grown rapidly both in Australia and overseas. Research on the industry has been wide-ranging, with one strand of the research involving a reassessment of labour process debates about managerial control and employee resistance. This reassessment has been partially sparked by the distinct technological features of call centre operations. Technical systems in call centres automatically distribute calls, and management have acquired an increased capability to measure and monitor employee performance and behaviour. These advances have led some scholars to argue that new heightened forms of control have emerged within the call centre industry. This article examines the extent and nature of monitoring in the call centres of two large telecommunications firms and analyses the way customer service representatives (CSRs) responded to such conditions. The article questions whether increased monitoring and surveillance, characteristic of the industry, can be conceptualised as a new form of totalising labour control. It suggests that control has not proved to be complete. As in other workplaces, workers have been able to undertake a variety of actions that attempt to restore a sense of power over their work conditions.

Is It Better to Forget? Stimulus-Response, Prediction, and the Weight of Past Experience in a Fast-Paced Bargaining Task

Decision makers in dynamic environments such as air traffic control, firefighting, and call center operations adapt in real-time using outcome feedback. Understanding this adaptation is important for influencing and improving the decisions made. Recently, stimulus-response (S-R) learning models have been proposed as explanations for decision makers' adaptation. S-R models hypothesize that decision makers choose an action option based on their anticipation of its success. Decision makers learn by accumulating evidence over action options and combining that evidence with prior expectations. This study examines a standard S-R model and a simple variation of this model, in which past experience may receive an extremely low weight, as explanations for decision makers' adaptation in an evolving Internet-based bargaining environment. In Experiment 1, decision makers are taught to predict behavior in a bargaining task that follows rules that may be the opposite of, congruent to, or unrelated to a second task in which they must choose the deal terms they will offer. Both models provide a good account of the prediction task. However, only the second model, in which decision makers heavily discount all but the most recent past experience, provides a good account of subsequent behavior in the second task. To test whether Experiment 1 artificially related choice behavior and prediction, a second experiment examines both models' predictions concerning the effects of bargaining experience on subsequent prediction. In this study, decision models where long-term experience plays a dominating role do not appear to provide adequate explanations of decision makers' adaptation to their opponent's changing response behavior.

Making Room for the Call Center

A call center can dramatically improve an organization's ability to serve its customers. in this article, three important questions are addressed for senior managers and executives who are establishing or expanding a call-center operation. First, as employees focus on responding to customer inquiries, will their skills become narrower and ultimately less beneficial to the organization? This article argues that skills for employees in call centers can and should be upgraded. Second, will the decentralized decision-making of the call center lead to a loss of managerial control? the article suggests ways of ensuring that the ideal configuration of decentralized decision making and centralized control takes hold in the organization after the call center is established. Third, how can an organization's teamwork and corporate spirit be maintained and enhanced after the establishment of a call center? the article offers practical advice for enhancing an organization's culture even as employees begin to spend less time in face-to-face interactions.