Using text-mining-assisted analysis to examine the applicability of unstructured data in the context of customer complaint management

Double Degree

Customer relationship management model - A strategic and analytical approach for Amorim Turismo

Field lab: Entrepreneurial and innovative ventures

UNDERSTANDING CUSTOMER CHOICES IN SERVICE OUTSOURCING AND REVENUE MANAGEMENT

This dissertation investigates customer behavior modeling in service outsourcing and revenue management in the service sector (i.e., airline and hotel industries). In particular, it focuses on a common theme of improving firms’ strategic decisions through the understanding of customer preferences. Decisions concerning degrees of outsourcing, such as firms’ capacity choices, are important to performance outcomes. These choices are especially important in high-customer-contact services (e.g., airline industry) because of the characteristics of services: simultaneity of consumption and production, and intangibility and perishability of the offering. Essay 1 estimates how outsourcing affects customer choices and market share in the airline industry, and consequently the revenue implications from outsourcing. However, outsourcing decisions are typically endogenous. A firm may choose whether to outsource or not based on what a firm expects to be the best outcome. Essay 2 contributes to the literature by proposing a structural model which could capture a firm’s profit-maximizing decision-making behavior in a market. This makes possible the prediction of consequences (i.e., performance outcomes) of future strategic moves. Another emerging area in service operations management is revenue management. Choice-based revenue systems incorporate discrete choice models into traditional revenue management algorithms. To successfully implement a choice-based revenue system, it is necessary to estimate customer preferences as a valid input to optimization algorithms. The third essay investigates how to estimate customer preferences when part of the market is consistently unobserved. This issue is especially prominent in choice-based revenue management systems. Normally a firm only has its own observed purchases, while those customers who purchase from competitors or do not make purchases are unobserved. Most current estimation procedures depend on unrealistic assumptions about customer arriving. This study proposes a new estimation methodology, which does not require any prior knowledge about the customer arrival process and allows for arbitrary demand distributions. Compared with previous methods, this model performs superior when the true demand is highly variable.

Simulating customer experience and word-of-mouth in retail: a case study

Agents offer a new and exciting way of understanding the world of work. In this paper we describe the development of agent-based simulation models, designed to help to understand the relationship between people management practices and retail performance. We report on the current development of our simulation models which includes new features concerning the evolution of customers over time. To test the features we have conducted a series of experiments dealing with customer pool sizes, standard and noise reduction modes, and the spread of customers’ word of mouth. To validate and evaluate our model, we introduce new performance measure specific to retail operations. We show that by varying different parameters in our model we can simulate a range of customer experiences leading to significant differences in performance measures. Ultimately, we are interested in better understanding the impact of changes in staff behavior due to changes in store management practices. Our multi-disciplinary research team draws upon expertise from work psychologists and computer scientists. Despite the fact we are working within a relatively novel and complex domain, it is clear that intelligent agents offer potential for fostering sustainable organizational capabilities in the future.

Customer Engagement kontzeptuaren barnerapena C2C merkataritza elektronikoan

[EU] Hurrengo lana, Consumer to Consumer merkataritza elektronikoan (hemendik aurrera, C2C) fokatuta dagoen azterketa da. C2C merkatu elektronikoaren esparruan kontsumitzaileak erosketa burutzera bultzatzen duten faktoreak identifikatu nahi dira. Horretarako, lehendabizi C2C merkataritza elektronikoaren ingurunea aztertuko da gainetik, gaia kokatzeko asmotan. Ingurune honetan artikulu zientifikoetan, gero eta nabarmentasun handiagoa hartzen ari den Customer Engagement edo kontsumitzailearen konpromisoa kontzeptuaren azterketa bat burutuko da. Kontzeptu hau hobeto ulertzeko asmotan, autore desberdinek eskainitako definizioak eta beste definizio baliagarri batzuk aurkituko ditugu. Behin kontzeptua definiturik, honek barneratzen duen zikloa identifikatzera pasatuko gara. Horretarako, Sashik 2012 urtean argitaratutako ikerketa lana hartu da oinarri lez. Autore honek egindako zikloari, ekarpen propio gisa, kontsumitzaileen jarrera ulertzen lagunduko diguten beste hainbat kontzeptu gehitu dira. Azkenik, aipatutako eta aztertutako kontzeptuak errealitatean identifikatzeko, azterketa praktiko bat burutu da. Azterketa honetan, teorian azaldutakoa, adibide errealen bidez identifikatzeaz gain, inkesta txiki bat aurkituko dugu. Honen bitartez, lan teorikoari erabilera praktikoago bat eman nahi izan zaio.

Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN

Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

Acceptance of smartphone-based mobile shopping:mobile benefits, customer characteristics, perceived risk and the impact of application context

Despite their generally increasing use, the adoption of mobile shopping applications often differs across purchase contexts. In order to advance our understanding of smartphone-based mobile shopping acceptance, this study integrates and extends existing approaches from technology acceptance literature by examining two previously underexplored aspects. Firstly, the study examines the impact of different mobile and personal benefits (instant connectivity, contextual value and hedonic motivation), customer characteristics (habit) and risk facets (financial, performance, and security risk) as antecedents of mobile shopping acceptance. Secondly, it is assumed that several acceptance drivers differ in relevance subject to the perception of three mobile shopping characteristics (location sensitivity, time criticality, and extent of control), while other drivers are assumed to matter independent of the context. Based on a dataset of 410 smartphone shoppers, empirical results demonstrate that several acceptance predictors are associated with ease of use and usefulness, which in turn affect intentional and behavioral outcomes. Furthermore, the extent to which risks and benefits impact ease of use and usefulness is influenced by the three contextual characteristics. From a managerial perspective, results show which factors to consider in the development of mobile shopping applications and in which different application contexts they matter.

Understanding the town centre customer experience (TCCE)

This research enhances the understanding of consumer behaviour and customer experience in the context of town centres. First, it defines town centre customer experience (TCCE) as a multifaceted journey that combines interactions with a diverse range of public and private organisations, including retailers and social and community elements; this results in a unique experience co-created with the consumer across a series of functional and experiential touchpoints. Second, combining qualitative and quantitative insights, this research reveals a series of specific functional and experiential TCCE touchpoints, which underpin the consumer internal response (motivation to visit) and outward behaviour (desire to stay and revisit intentions) in the town centre. In addition to enhancing town centre and customer experience knowledge, these findings offer important new insights to those managing town centres and seeking to retain customer loyalty in the high street. Above all, these findings can help identify the touchpoints that need to be reinforced and/or improved to differentiate a town from its competing centres and to create tailored marketing strategies. Taken together, such initiatives have the potential to positively impact the revitalisation of the high street and the town centre economy.

Intersubjectivity and sentiment:from language to knowledge

Intersubjectivity is an important concept in psychology and sociology. It refers to sharing conceptualizations through social interactions in a community and using such shared conceptualization as a resource to interpret things that happen in everyday life. In this work, we make use of intersubjectivity as the basis to model shared stance and subjectivity for sentiment analysis. We construct an intersubjectivity network which links review writers, terms they used, as well as the polarities of the terms. Based on this network model, we propose a method to learn writer embeddings which are subsequently incorporated into a convolutional neural network for sentiment analysis. Evaluations on the IMDB, Yelp 2013 and Yelp 2014 datasets show that the proposed approach has achieved the state-of-the-art performance.

Différences sur le plan de la motivation au travail, de la capacité de résilience et du sentiment d’efficacité personnelle en classe et à l’école des enseignants débutants selon leur participation à des programmes d’insertion professionnelle offerts dans leurs commissions scolaires d’attache

Actuellement au Québec, le contexte d’insertion professionnelle en enseignement représente plusieurs défis pour les enseignants débutants, et ce, en raison de multiples causes (p.ex. la précarité et le manque de soutien). Résultat : près de 15 % à 20 % d’entre eux quitteront la profession dans les cinq premières années de leur carrière et cette statistique ne cesse d’augmenter. Pour remédier à la situation, l’une des solutions envisagées est la mise en place de programmes d’insertion professionnelle (PIP) par les commissions scolaires, lesquels offrent différentes mesures de soutien telles que du mentorat, des ateliers de formation et des réseaux d’entraide en ligne. Cela dit, les modalités de mise en place de ces programmes varient grandement d’un milieu à l’autre, et ce, autant en ce qui a trait aux services offerts qu’à l’admission des candidats. De plus, ceux-ci ne sont généralement évalués que de façon informelle par le milieu. On ne sait donc pas si les enseignants débutants qui y participent se distinguent réellement quant à leur persévérance dans le métier, laquelle repose notamment sur leur motivation au travail, leur capacité de résilience et leur sentiment d’efficacité personnelle (SEP) en classe et à l’école (Bandura, 1997, 2007; Bélair & Lebel, 2007; Deci & Ryan, 1985, 2002; Fernet, Sénécal, Guay, Marsh, & Dowson, 2008; Zacharyas & Brunet, 2012). Ce projet de recherche vise d’une part à mesurer les différences sur le plan de ces variables chez les enseignants débutants participant ou non à un PIP. D’autre part, il vise également à mesurer la prédiction de ces variables par les différentes mesures de soutien offertes dans les PIP chez ceux qui y participent pour constater leur contribution respective dans un PIP. Pour ce faire, une étude préexpérimentale a été menée auprès de 86 participants. À l’aide d’un questionnaire, la motivation au travail, la capacité de résilience et le SEP en classe et à l’école ont été mesurés afin de comparer les résultats du groupe d’enseignants participant à un programme à ceux n’y participant pas. Une MANCOVA a d’abord été conduite avec ces variables et trois variables contrôles « avoir pensé quitter » le milieu d’enseignement, « ordre d’enseignement » et « expérience d’enseignement » comme covariables. Des régressions linéaires multivariées ont ensuite été menées à partir des mesures de soutien. Aucun résultat significatif n’a été obtenu quant aux différences entre les participants en fonction de la participation à un PIP ce qui est représentatif des résultats obtenus dans d’autres recherches sur le sujet (Ingersoll & Strong, 2011). Aucun résultat significatif n’a été obtenu concernant la prédiction des variables d’intérêt par les mesures de soutien.

Communication across cultures? An intercultural approach to customer service in the hotel industry: a study with globally branded hotels in the United Kingdom

In a professional and business-social context such as that of global hotel brands in the United Kingdom, intercultural communication, contacts and relationships are found at the heart of daily operations and of customer service. A large part of the clientele base of hotels in the United Kingdom is formed by individuals who belong to different cultural groups that travel in the country either for leisure or business. At the same time, the global workforce which is recruited in the hotel industry in the United Kingdom is a reality here to stay. Global travelling and labor work mobility are phenomena which have been generated by changes which occur on a socio-economic, cultural and political level due to the phenomenon of globalization. The hotel industry is therefore well acquainted with the essence of different cultures either to be accommodated within hotel premises, as in the case of external customers, or of diversity management where different cultures are recruited in the hotel industry, as in the case of internal customers. This thesis derives from research conducted on eight different global hotel brands in the United Kingdom in particular, with reference to three, four and five star categories. The research aimed to answer the question of how hotels are organized in order to address issues of intercultural communication during customer service and if intercultural barriers arise during the intercultural interaction of hotel staff and global customers. So as to understand how global hotel brands operate the research carried out focused in three main areas relating to each hotel: organizational culture, customer service–customer care and intercultural issues. The study utilized qualitative interviews with hotel management staff and non-management staff from different cultural backgrounds, public space observations between customers and staff during check-in and checkout in the reception area and during dining at the café-bar and restaurant. Thematic analysis was also applied to the official web page of each hotel and to job advertisements to enhance the findings from the interviews and the observations. For the process of analysis of the data interpretive (hermeneutic) phenomenology of Martin Heidegger has been applied. Generally, it was found that hotel staff quite often feel perplexed by how to deal with and how to overcome, for instance, language barriers and religious issues and how to interpret non verbal behaviors or matters on food culture relating to the intercultural aspect of customer service. In addition, it was interesting to find that attention to excellent customer service on the part of hotel staff is a top organizational value and customer care is a priority. Despite that, the participating hotel brands appear to have not yet, realized how intercultural barriers can affect the daily operation of the hotel, the job performance and the psychology of hotel staff. Employees indicated that they were keen to receive diversity training, provided by their organizations, so as to learn about different cultural needs and expand their intercultural skills. The notion of diversity training in global hotel brands is based on the sense that one of the multiple aims of diversity management as a practice and policy in the workplace of hotels is the better understanding of intercultural differences. Therefore global hotel brands can consider diversity training as a practice which will benefit their hotel staff and clientele base at the same time. This can have a distinctive organizational advantage for organizational affairs in the hotel industry, with potential to influence the effectiveness and performance of hotels.

Customer Loyalty toward grocery retailing service: a multidimensional approach to costumer perceived value

Structured abstract Purpose: To deepen, in grocery retail context, the roles of consumer perceived value and consumer satisfaction, as antecedents’ dimensions of customer loyalty intentions. Design/Methodology/approach: Also employing a short version (12-items) of the original 19-item PERVAL scale of Sweeney & Soutar (2001), a structural equation modeling approach was applied to investigate statistical properties of the indirect influence on loyalty of a reflective second order customer perceived value model. The performance of three alternative estimation methods was compared through bootstrapping techniques. Findings: Results provided i) support for the use of the short form of the PERVAL scale in measuring consumer perceived value; ii) the influence of the four highly correlated independent latent predictors on satisfaction was well summarized by a higher-order reflective specification of consumer perceived value; iii) emotional and functional dimensions were determinants for the relationship with the retailer; iv) parameter’s bias with the three methods of estimation was only significant for bootstrap small sample sizes. Research limitations:/implications: Future research is needed to explore the use of the short form of the PERVAL scale in more homogeneous groups of consumers. Originality/value: Firstly, to indirectly explain customer loyalty mediated by customer satisfaction it was adopted a recent short form of PERVAL scale and a second order reflective conceptualization of value. Secondly, three alternative estimation methods were used and compared through bootstrapping and simulation procedures.

Experimenting with the role of performance of hygiene and motivators on customer satisfaction: studying the temporal effect

Marketers continuously attempt to identify important attributes and innovate in order to understand how attribute performance could lead to customer satisfaction in the short term and in the long term. Understanding the impact of customer satisfaction may offer a competitive edge to companies. Researchers are discussing the importance of performance attributes in leading to satisfaction; however, there is no clear understanding of whether an attribute that leads to satisfaction at one time (e.g., short run) can cause it also in the long run, without excluding the possibility that it could lead to dissatisfaction and no satisfaction. The present research tries to understand anomalies related to asymmetric attribute performance and satisfaction over time with the help of Herzberg's (1967) Two-Factor Theory (TFT) and construal level theory (CLT). More precisely, there are main purposes of this dissertation. First, the present research tries to understand whether positive or negative hygiene attribute performance and motivator attribute factors exert different weights on overall customer satisfaction depending on the time elapsed from the service experience. Second, to test if positive or negative hygiene/motivator attribute performance affect to revisit intention and to word of mouth by considering mediating role of satisfaction. The results reveal that in the near past (NP) experience, the positive performance of hygiene concrete attributes creates a differential effect on overall satisfaction higher than the negative performance of hygiene concrete attributes. Results also confirmed mediating role of satisfaction in the relationship between attribute performance and revisit intention for near past condition but not for distant past. Likewise significant relationship was found for the mediating role of satisfaction in the relationship between attribute performance and word of mouth (WOM) for near past condition but not for distant past.

Progettazione ed Implementazione Front-End di un Sistema Integrato di Customer Assistance in ambito Industry 4.0

Al giorno d'oggi, l'industry 4.0 è un movimento sempre più prominente che induce ad equipaggiare gli impianti industriali con avanzate infrastrutture tecnologiche digitali, le quali operano sinergicamente con l'impianto, al fine di controllare ed aumentare la produttività, monitorare e prevenire i futuri guasti, ed altro ancora. In questo ambito, gli utenti sono parte integrante della struttura produttiva, in cui ricoprono ruoli strategici e flessibili, collaborano fra loro e con le macchine, con l’obiettivo di affrontare e risolvere proattivamente una vasta gamma di problemi complessi. In particolare, la customer assistance nel settore industriale può certamente variare in relazione a molteplici elementi: il tipo di produzione e le caratteristiche del prodotto; l'organizzazione ed infrastruttura aziendale interna; la quantità di risorse disponibili che possono essere impiegate; il grado di importanza ricoperto dalla customer assistance nel settore industriale di riferimento; altri eventuali fattori appartenenti ad un dominio specifico. Per queste ragioni, si è cercato di individuare e categorizzare nel modo più accurato possibile, il lavoro svolto in questo elaborato ed il contesto nel quale è stato sviluppato. In questa tesi, viene descritta un'applicazione web per erogare assistenza al cliente in ambito di industria 4.0, attraverso il paradigma di ticketing o ticket di supporto/assistenza. Questa applicazione è integrata nel sistema Mentor, il quale è attivo già da anni nel settore industriale 4.0. Il progetto Mentor è una suite di applicazioni cloud-based creata dal gruppo Bucci Industries, una multinazionale attiva nell'industria e nell'automazione con sede a Faenza. In questo caso di studio, si presenta la progettazione ed implementazione della parte front-end del suddetto sistema di assistenza, il quale è integrato ed interconnesso con un paio di applicazioni tipiche di industria 4.0, presenti nella stessa suite di applicazioni.

Sentiment analysis: la guerra russo-ucraina su twitter

Nel corso dell’elaborato verranno utilizzate tecniche e strumenti di analisi automatica di dati aventi carattere testuale. Lo scopo del lavoro di tesi consisterà nel condurre text mining e sentiment analysis su dei messaggi al fine di comprenderne il significato, con interesse particolare sulle emozioni ed i sentimenti in essi contenuti per riuscire ad estrapolare informazioni di interesse.