Sentiment classification with case-base approach

L’augmentation de la croissance des réseaux, des blogs et des utilisateurs des sites d’examen sociaux font d’Internet une énorme source de données, en particulier sur la façon dont les gens pensent, sentent et agissent envers différentes questions. Ces jours-ci, les opinions des gens jouent un rôle important dans la politique, l’industrie, l’éducation, etc. Alors, les gouvernements, les grandes et petites industries, les instituts universitaires, les entreprises et les individus cherchent à étudier des techniques automatiques fin d’extraire les informations dont ils ont besoin dans les larges volumes de données. L’analyse des sentiments est une véritable réponse à ce besoin. Elle est une application de traitement du langage naturel et linguistique informatique qui se compose de techniques de pointe telles que l’apprentissage machine et les modèles de langue pour capturer les évaluations positives, négatives ou neutre, avec ou sans leur force, dans des texte brut. Dans ce mémoire, nous étudions une approche basée sur les cas pour l’analyse des sentiments au niveau des documents. Notre approche basée sur les cas génère un classificateur binaire qui utilise un ensemble de documents classifies, et cinq lexiques de sentiments différents pour extraire la polarité sur les scores correspondants aux commentaires. Puisque l’analyse des sentiments est en soi une tâche dépendante du domaine qui rend le travail difficile et coûteux, nous appliquons une approche «cross domain» en basant notre classificateur sur les six différents domaines au lieu de le limiter à un seul domaine. Pour améliorer la précision de la classification, nous ajoutons la détection de la négation comme une partie de notre algorithme. En outre, pour améliorer la performance de notre approche, quelques modifications innovantes sont appliquées. Il est intéressant de mentionner que notre approche ouvre la voie à nouveaux développements en ajoutant plus de lexiques de sentiment et ensembles de données à l’avenir.

Analisi di un Sistema di Stoccaggio. L’attività di Customer Service. Il caso Due Torri S.p.A.

Si è analizzato un sistema di stoccaggio rivolgendo l'attenzione all'attività del Customer Service. Dopo il primo periodo di raccolta dati è stato popolato un database che rappresentasse al meglio la realtà osservata. Il database ci ha permesso, attraverso la manipolazione dei dati, di calcolare delle statistiche circa gli eventi più significativi in termini di tempo.

Management of Customer Co-development in Business-to-Business Markets

Management of customer co-development means involving customers in the development of new products and services, and coordinating the process. In business-tobusiness markets, customer co-development enables the development of innovations that better match customer needs and strengthens customer relationships. However, close collaboration with customers can hamper the innovativeness of new products and lead to overly customized solutions. Therefore, the management of co-development is crucial to its success. Yet the existing research on management of co-development has mainly focused on selecting the right collaboration partners, and the field lacks understanding on how to manage the tensions inherent in customer co-development. The purpose of this thesis is to increase understanding on the management of the codevelopment. The thesis is divided into two parts. The first comprises the literature review and conclusions for the whole study, and the second presents four publications. From the methodological perspective, the research papers follow exploratory qualitative research design. The empirical data comprise interviews with 60 persons, representing 25 different organizations, and a group of 11 end users. The study conceptualizes management of customer co-development in three dimensions 1) relational co-development processes, 2) co-development challenges and paradoxes, and 3) internal customer involvement processes. The findings contribute to the customersupplier relationship, innovation, and marketing management literatures by providing a framework on supplier-customer co-development, addressing co-development paradoxes and their management processes, and suggesting practices for customer involvement. For practitioners, the findings provide tools to manage the challenges related to codevelopment with customers.

Customer stimulation in lean software development

The process of developing software is a complex undertaking involving multiple stakeholders. While the intentions of these parties might vary to some extent, the ultimate goal can be seen as a satisfactory product. Lean and agile software development practices strive toward this and they place customer contentment as one of the highest aims of the process. An important aspect of any development process is the act of innovation. Without it, nothing progresses and the whole process is unnecessary. As a target domain expert, the customer is an important part of effective innovation. Problems arise, however, when the customer is not actively taking part in the activities. Lack of familiarity with software development can easily cause such issues. Unfortunately, the amount of research conducted on product innovation is unimpressive. This makes it difficult to formulate a recommended approach on stimulating the customer and encouraging a more active participation. Ultimately, a small set of high-level guidelines were identified from the available literary resources for inducing innovation. To conclude, this thesis presents the findings made during the development of a small web application and compares them to the aforementioned literature findings. While the guidelines seem to provide promising results, further empirical research is needed to attain more significant conclusions.

Selling customer value in B2B markets - Case KONE JumpLift

Skepticism of promised value-added is forcing suppliers to provide tangible evidence of the value they can deliver for the customers in industrial markets. Despite this, quantifying customer benefits is being thought as one of the most difficult part in business-to-business selling. The objective of this research is to identify the desired and perceived customer benefits of KONE JumpLift™ and improve the overall customer value quantification and selling process of the solution. The study was conducted with a qualitative case analysis including 7 interviews with key stakeholders from three different market areas. The market areas were chosen based on where the offering has been utilized and the research was conducted by five telephone and two email interviews. The main desired and perceived benefits include many different values for example economical, functional, symbolic and epistemic value but they vary on studied market areas. The most important result of the research was finding the biggest challenges of selling the offering which are communicating and proving the potential value to the customers. In addition, the sales arguments have different relative importance in studied market areas which create challenges for salespeople to sell the offering effectively. In managerial level this means need for investing into a new sales tool and training the salespeople.

Contextual text mining

With the dramatic growth of text information, there is an increasing need for powerful text mining systems that can automatically discover useful knowledge from text. Text is generally associated with all kinds of contextual information. Those contexts can be explicit, such as the time and the location where a blog article is written, and the author(s) of a biomedical publication, or implicit, such as the positive or negative sentiment that an author had when she wrote a product review; there may also be complex context such as the social network of the authors. Many applications require analysis of topic patterns over different contexts. For instance, analysis of search logs in the context of the user can reveal how we can improve the quality of a search engine by optimizing the search results according to particular users; analysis of customer reviews in the context of positive and negative sentiments can help the user summarize public opinions about a product; analysis of blogs or scientific publications in the context of a social network can facilitate discovery of more meaningful topical communities. Since context information significantly affects the choices of topics and language made by authors, in general, it is very important to incorporate it into analyzing and mining text data. In general, modeling the context in text, discovering contextual patterns of language units and topics from text, a general task which we refer to as Contextual Text Mining, has widespread applications in text mining. In this thesis, we provide a novel and systematic study of contextual text mining, which is a new paradigm of text mining treating context information as the ``first-class citizen.'' We formally define the problem of contextual text mining and its basic tasks, and propose a general framework for contextual text mining based on generative modeling of text. This conceptual framework provides general guidance on text mining problems with context information and can be instantiated into many real tasks, including the general problem of contextual topic analysis. We formally present a functional framework for contextual topic analysis, with a general contextual topic model and its various versions, which can effectively solve the text mining problems in a lot of real world applications. We further introduce general components of contextual topic analysis, by adding priors to contextual topic models to incorporate prior knowledge, regularizing contextual topic models with dependency structure of context, and postprocessing contextual patterns to extract refined patterns. The refinements on the general contextual topic model naturally lead to a variety of probabilistic models which incorporate different types of context and various assumptions and constraints. These special versions of the contextual topic model are proved effective in a variety of real applications involving topics and explicit contexts, implicit contexts, and complex contexts. We then introduce a postprocessing procedure for contextual patterns, by generating meaningful labels for multinomial context models. This method provides a general way to interpret text mining results for real users. By applying contextual text mining in the ``context'' of other text information management tasks, including ad hoc text retrieval and web search, we further prove the effectiveness of contextual text mining techniques in a quantitative way with large scale datasets. The framework of contextual text mining not only unifies many explorations of text analysis with context information, but also opens up many new possibilities for future research directions in text mining.

Identifying New Business Opportunities and Customer Value Creation: Case Vuosaari

Previously conducted research projects in the field of logistics services have emphasized the importance of value added services in customer value creation. Through value added services companies can extend their service portfolio and gain higher customer satisfaction and loyalty. In more general level service marketing has been recognized to be challenging due the intangible nature of services. This has caused issues in pricing and value perceptions. To tackle these issues scholars have suggested well–managed customer reference marketing practices. The main goal of this research work is to identify shortages in the current service offering. Additionally, the focus is on, how these shortages can be fixed. Due the low capacity utilization of warehouse premises, there is a need to find the main factors, which are causing or affecting on the current situation. The research aims to offer a set of alternatives how to come over these issues. All the potential business opportunities are evaluated and the promising prospects are discussed. The focus is on logistics value added services and how those effect on route decisions in logistics. Simultaneously the aim is to create a holistic understanding of how added value and offered services effect on logistics centralization. Moreover, customer value creation and customer references’ effectiveness in logistics service marketing are emphasized in this project. Logistics value added services have a minor effect on logistics decision. Routes are chosen on a low–cost basis. However, it is challenging to track down logistics costs and break those down into different phases. Customer value as such is a difficult concept. This causes challenges when services are sold with value–based principles. Customer references are useful for logistics service providers and this should be exploited in marketing. Those reduce the perceived risk and give credibility to the service provider.

Customer Support, Motivation to participate and participation in services : a first step.

International audience

Development of project management procedures for customer project business

Objective of the thesis is to develop project management procedure for chilled beam projects. In organization is recognized that project management techniques could help in large and complex projects. Information sharing have been challenging in projects, so improvement of information sharing is one key topic of the thesis. Academic researches and literature are used to find suitable project management theories and methods. Main theories are related to phases of the project and project management tools. Practical knowledge of project management is collected from two project business oriented companies. Project management tools are chosen and modified to fulfill needs of the beam projects. Result of the thesis is proposed project management procedure, which includes phases of the chilled beam projects and project milestones. Project management procedure helps to recognize the most critical phases of the project and tools help to manage information of the project. Procedure increases knowledge of the project management techniques and tools. It also forms coherent project management working method among the chilled beam project group.

Creating and measuring customer value in digital businesses

Most economic transactions nowadays are due to the effective exchange of information in which digital resources play a huge role. New actors are coming into existence all the time, so organizations are facing difficulties in keeping their current customers and attracting new customer segments and markets. Companies are trying to find the key to their success and creating superior customer value seems to be one solution. Digital technologies can be used to deliver value to customers in ways that extend customers’ normal conscious experiences in the context of time and space. By creating customer value, companies can gain the increased loyalty of existing customers and better ways to serve new customers effectively. Based on these assumptions, the objective of this study was to design a framework to enable organizations to create customer value in digital business. The research was carried out as a literature review and an empirical study, which consisted of a web-based survey and semi-structured interviews. The data from the empirical study was analyzed as mixed research with qualitative and quantitative methods. These methods were used since the object of the study was to gain deeper understanding about an existing phenomena. Therefore, the study used statistical procedures and value creation is described as a phenomenon. The framework was designed first based on the literature and updated based on the findings from the empirical study. As a result, relationship, understanding the customer, focusing on the core product or service, the product or service quality, incremental innovations, service range, corporate identity, and networks were chosen as the top elements of customer value creation. Measures for these elements were identified. With the measures, companies can manage the elements in value creation when dealing with present and future customers and also manage the operations of the company. In conclusion, creating customer value requires understanding the customer and a lot of information sharing, which can be eased by digital resources. Understanding the customer helps to produce products and services that fulfill customers’ needs and desires. This could result in increased sales and make it easier to establish efficient processes.

Customer involvement in new service development

This case study aims at filling the research gap in the literature, by researching how customers experience customer involvement in new service development, in addition to giving insight on what are the organisational customers’ motivations to become involved in service development. These subjects are studied by conducting three interviews. The thesis gives a review of previous findings regarding customer-driven new service development, customer involvement, customer roles, modes of involvement, communication in the involvement process, what is the role of customer engagement and what are the motivational drivers for customers. The thesis also explains what new service development is and makes a distinction between new service development and new service design. The results revealed that organisational customers want to be involved throughout the development process, with active involvement in the beginning and end phases. Moreover, customers prefer face-to-face methods and active and bidirectional communication throughout the process. The findings propose seven motivational factors, a new framework for customer-driven new service development and communication process map. The managerial implications list five themes for service providers to take into consideration when involving customers to the service development process.

Multi-class sentiment analysis using a hierarchical logistic model tree approach

En este trabajo se propone un nuevo sistema híbrido para el análisis de sentimientos en clase múltiple basado en el uso del diccionario General Inquirer (GI) y un enfoque jerárquico del clasificador Logistic Model Tree (LMT). Este nuevo sistema se compone de tres capas, la capa bipolar (BL) que consta de un LMT (LMT-1) para la clasificación de la polaridad de sentimientos, mientras que la segunda capa es la capa de la Intensidad (IL) y comprende dos LMTs (LMT-2 y LMT3) para detectar por separado tres intensidades de sentimientos positivos y tres intensidades de sentimientos negativos. Sólo en la fase de construcción, la capa de Agrupación (GL) se utiliza para agrupar las instancias positivas y negativas mediante el empleo de 2 k-means, respectivamente. En la fase de Pre-procesamiento, los textos son segmentados por palabras que son etiquetadas, reducidas a sus raíces y sometidas finalmente al diccionario GI con el objetivo de contar y etiquetar sólo los verbos, los sustantivos, los adjetivos y los adverbios con 24 marcadores que se utilizan luego para calcular los vectores de características. En la fase de Clasificación de Sentimientos, los vectores de características se introducen primero al LMT-1, a continuación, se agrupan en GL según la etiqueta de clase, después se etiquetan estos grupos de forma manual, y finalmente las instancias positivas son introducidas a LMT-2 y las instancias negativas a LMT-3. Los tres árboles están entrenados y evaluados usando las bases de datos Movie Review y SenTube con validación cruzada estratificada de 10-pliegues. LMT-1 produce un árbol de 48 hojas y 95 de tamaño, con 90,88% de exactitud, mientras que tanto LMT-2 y LMT-3 proporcionan dos árboles de una hoja y uno de tamaño, con 99,28% y 99,37% de exactitud,respectivamente. Los experimentos muestran que la metodología de clasificación jerárquica propuesta da un mejor rendimiento en comparación con otros enfoques prevalecientes.

Customer needs in innovation and R&D strategy development

Tutkimuksen kohteena oleva yritys avasi innovaatiokeskuksen 2015 vuoden loppupuolella. Tutkimuksen tavoite on tutkia keinoja löytää asiakastarpeita innovaatiokeskuksessa sekä selvittää, kuinka asiakastarpeet sisällytetään innovaatio- ja tuotekehitysstrategiaan. Kattava prosessi asiakastarvekartoituksesta esitellään ja prosessi säädetään yritykselle sopivaksi asiakkaille tehdyn kyselyn tulosten mukaan. Lisäksi yrityksen tuotepäälliköille järjestettiin haastattelu, jotta heidän näkemyksiään asiakastarvekartoituksen kehittämisestä ja tarpeiden lisäämisestä strategiaan päästiin myös hyödyntämään. Asiakastarpeiden kartoittamiseen soveltuvaksi menetelmäksi löydettiin ryhmätyömalliin perustuva menetelmä, jossa tarpeita kerätään innovaatiokeskuksessa. Lisäksi tietokoneita hyödyntävä GDSS-kokous auttaa välttämään useita yleisiä kokousten ongelmia. Tutkimuksen mukaan asiakastarpeiden suuret kehityslinjat ja kaikista tärkeimmät tarpeet voidaan lisätä strategiaan hyödyntämällä innovaatiokenttiä, skenaarioita ja roadmappeja sekä asiakastarvetaulukkoja.

An agent-based simulation of in-store customer experiences

Agent-based modelling and simulation offers a new and exciting way of understanding the world of work. In this paper we describe the development of an agent-based simulation model, designed to help to understand the relationship between human resource management practices and retail productivity. We report on the current development of our simulation model which includes new features concerning the evolution of customers over time. To test some of these features we have conducted a series of experiments dealing with customer pool sizes, standard and noise reduction modes, and the spread of the word of mouth. Our multidisciplinary 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 organisational capabilities in the future.