Product feature taxonomy learning based on user reviews

In recent years, the Web 2.0 has provided considerable facilities for people to create, share and exchange information and ideas. Upon this, the user generated content, such as reviews, has exploded. Such data provide a rich source to exploit in order to identify the information associated with specific reviewed items. Opinion mining has been widely used to identify the significant features of items (e.g., cameras) based upon user reviews. Feature extraction is the most critical step to identify useful information from texts. Most existing approaches only find individual features about a product without revealing the structural relationships between the features which usually exist. In this paper, we propose an approach to extract features and feature relationships, represented as a tree structure called feature taxonomy, based on frequent patterns and associations between patterns derived from user reviews. The generated feature taxonomy profiles the product at multiple levels and provides more detailed information about the product. Our experiment results based on some popularly used review datasets show that our proposed approach is able to capture the product features and relations effectively.

A review selection method using product feature taxonomy

As of today, online reviews have become more and more important in decision making process. In recent years, the problem of identifying useful reviews for users has attracted significant attentions. For instance, in order to select reviews that focus on a particular feature, researchers proposed a method which extracts all associated words of this feature as the relevant information to evaluate and find appropriate reviews. However, the extraction of associated words is not that accurate due to the noise in free review text, and this affects the overall performance negatively. In this paper, we propose a method to select reviews according to a given feature by using a review model generated based upon a domain ontology called product feature taxonomy. The proposed review model provides relevant information about the hierarchical relationships of the features in the review which captures the review characteristics accurately. Our experiment results based on real world review dataset show that our approach is able to improve the review selection performance according to the given criteria effectively.

Quality-aware review selection based on product feature taxonomy

As of today, user-generated information such as online reviews has become increasingly significant for customers in decision making process. Meanwhile, as the volume of online reviews proliferates, there is an insistent demand to help the users tackle the information overload problem. In order to extract useful information from overwhelming reviews, considerable work has been proposed such as review summarization and review selection. Particularly, to avoid the redundant information, researchers attempt to select a small set of reviews to represent the entire review corpus by preserving its statistical properties (e.g., opinion distribution). However, one significant drawback of the existing works is that they only measure the utility of the extracted reviews as a whole without considering the quality of each individual review. As a result, the set of chosen reviews may consist of low-quality ones even its statistical property is close to that of the original review corpus, which is not preferred by the users. In this paper, we proposed a review selection method which takes review quality into consideration during the selection process. Specifically, we examine the relationships between product features based upon a domain ontology to capture the review characteristics based on which to select reviews that have good quality and preserve the opinion distribution as well. Our experimental results based on real world review datasets demonstrate that our proposed approach is feasible and able to improve the performance of the review selection effectively.

Generating product feature hierarchy from product reviews

User generated information such as product reviews have been booming due to the advent of web 2.0. In particular, rich information associated with reviewed products has been buried in such big data. In order to facilitate identifying useful information from product (e.g., cameras) reviews, opinion mining has been proposed and widely used in recent years. In detail, as the most critical step of opinion mining, feature extraction aims to extract significant product features from review texts. However, most existing approaches only find individual features rather than identifying the hierarchical relationships between the product features. In this paper, we propose an approach which finds both features and feature relationships, structured as a feature hierarchy which is referred to as feature taxonomy in the remainder of the paper. Specifically, by making use of frequent patterns and association rules, we construct the feature taxonomy to profile the product at multiple levels instead of single level, which provides more detailed information about the product. The experiment which has been conducted based upon some real world review datasets shows that our proposed method is capable of identifying product features and relations effectively.

Advertising new product categories to new geographical markets

Em um ambiente global dinâmico e competitivo, muitas empresas notam que constante desenvolvimento e lançamento de novos produtos são atividades-chave para seu crescimento e sobrevivência. Hoje, um dos maiores desafios enfrentados por tais empresas envolve saber como agir em um mundo em que tanto o escopo como a estrutura do ambiente competitivo estão em constante mudança, e em que reestruturações e mudanças de portfólio são centrais para as companhias que visam capitalizar com o crescimento global. Tanto o rápido ritmo de inovação tecnológica quando a crescente afluência de economias emergentes apresentam riscos e oportunidades para as empresas, o que torna importante não apenas que estas estejam atentas ao lançamento de produtos de última geração para mercados desenvolvidos: faz-se também necessário que saibam como lançar produtos antigos para novos mercados. Usando o mercado brasileiro como um exemplo, esta dissertação procurou estudar como multinacionais têm utilizado anúncios publicitários no lançamento, para novos mercados, de categorias e subcategorias de produtos já vendidas em outros países. Após uma revisão da literatura disponível, do desenvolvimento de proposições, e da avaliação destas através de três estudos de caso, foi possível verificar a existência de alguma linearidade entre os casos e a literatura estudada, incluindo: uma busca pela legitimação da categoria que precede àquela pela da marca; o uso de “especialistas” para a legitimação da categoria; o uso de apelos baseados em argumentos; e a divulgação de mais de uma característica de produto por anúncio. No entanto, dadas algumas discrepâncias entre o que foi observado nos casos e aquilo descrito na literatura consultada, também foi possível verificar que a maneira como os anúncios são feitos em diferentes lugares depende igualmente do cenário competitivo enfrentado pela empresa, bem como de variantes econômicas e culturais específicas da localidade em questão.

Brand formative design - development and assessment of product design from a future, brand and consumer perspective

With this dissertation research we investigate intersections between design and marketing and in this respect, which factors do contribute that a product design becomes brand formative. We have developed a Brand Formative Design (BFD) framework, which investigates individual design features in a holistic, comparable, brand relevant, and consumer specific context. We discuss what kinds of characteristics contribute to BFD but also illuminate how they should be applied and examine: rnA holistic framework leading to Brand Formative Design. Identification and assessment of BFD Drivers. The dissection of products into three Distinctive Design Levels. The detection of surprising design preferences. The appropriate degree of scheme deviation with evolutionary design. Simulated BFD development processes with three different products and the integration of consumers. Future oriented objectification, comparability and assessment of design. Recommendations for the management of design in a brand specific context. Design is a product feature, which contributes significantly to the success of products. However, the development of new design contains challenges. Design can hardly be objectified; many people have an opinion concerning the attractiveness of new products but cannot formulate their future preferences. Product design is widely developed based on intuition, which can be difficult for the management of design. Here the concept of Brand Formative Design can provide a framework which contributes to structure, objectify, develop and assess new evolutionary design in brand and future relevant contexts, but also integrates consumers and their preferences without restricting creativity too much.

Unified Taxonomy for Reference Ontology of Shape Features in Product Model

This paper presents a unified taxonomy of shape features. Such taxonomy is required to construct ontologies to address heterogeneity in product/shape models. Literature provides separate classifications for volumetric, deformation and free-form surface features. The unified taxonomy proposed allows classification, representation and extraction of shape features in a product model. The novelty of the taxonomy is that the classification is based purely on shape entities and therefore it is possible to automatically extract the features from any shape model. This enables the use of this taxonomy to build reference ontology.

Evolution feature oriented model driven product line engineering approach for synergistic and dynamic service evolution in Clouds: four kinds of schema.

The proposed research will focus on developing a novel approach to solve Software Service Evolution problems in Computing Clouds. The approach will support dynamic evolution of the software service in clouds via a set of discovered evolution patterns. An initial survey informed us that such an approach does not exist yet and is in urgent need. Evolution Requirement can be classified into evolution features; researchers can describe the whole requirement by using evolution feature typology, the typology will define the relation and dependency between each features. After the evolution feature typology has been constructed, evolution model will be created to make the evolution more specific. Aspect oriented approach can be used for enhance evolution feature-model modularity. Aspect template code generation technique will be used for model transformation in the end. Product Line Engineering contains all the essential components for driving the whole evolution process.

Evolution feature oriented model driven product line engineering approach for synergistic and dynamic service evolution in clouds: A04BPEL3.0 proposal.

Model Driven based approach for Service Evolution in Clouds will mainly focus on the reusable evolution patterns' advantage to solve evolution problems. During the process, evolution pattern will be driven by MDA models to pattern aspects. Weaving the aspects into service based process by using Aspect-Oriented extended BPEL engine at runtime will be the dynamic feature of the evolution.

A study of entrepreneurship : Taiwanese digital content companies in China

China’s accession to the World Trade Organisation (WTO) has greatly enhanced global interest in investment in the Chinese media market, where demand for digital content is growing rapidly. The East Asian region is positioned as a growth area in many forms of digital content and digital service industries. China is attempting to catch up and take its place as a production centre to offset challenges from neighbouring countries. Meanwhile, Taiwan is seeking to use China both as an export market and as a production site for its digital content. This research investigates entry strategies of Taiwanese digital content firms into the Chinese market. By examining the strategies of a sample of Taiwan-based companies, this study also explores the evolution of their market strategies. However, the focus is on how distinctive business practices such as guanxi are important to Taiwanese business and to relations with Mainland China. This research examines how entrepreneurs manage the characteristics of digital content products and in turn how digital content entrepreneurs adapt to changing market circumstances. This project selected five Taiwan-based digital content companies that have business operations in China: Wang Film, Artkey, CnYES, Somode and iPartment. The study involved a field trip, undertaken between November 2006 and March 2007 to Shanghai and Taiwan to conduct interviews and to gather documentation and archival reports. Six senior managers and nine experts were interviewed. Data were analysed according to Miller’s firm-level entrepreneurship theory, foreign direct investment theory, Life Cycle Model and guanxi philosophy. Most studies of SMEs have focused on free market (capitalist) environments. In contrast, this thesis examines how Taiwanese digital content firms’ strategies apply in the Chinese market. I identified three main types of business strategy: cost-reduction, innovation and quality-enhancement; and four categories of functional strategies: product, marketing, resource acquisition and organizational restructuring. In this study, I introduce the concept of ‘entrepreneurial guanxi’, special relationships that imply mutual obligation, assurance and understanding to secure and exchange favors in entrepreneurial activities. While guanxi is a feature of many studies of business in Pan-Chinese society, it plays an important mediating role in digital content industries. In this thesis, I integrate the ‘Life Cycle Model’ with the dynamic concept of strategy. I outline the significant differences in the evolution of strategy between two types of digital content companies: off-line firms (Wang Film and Artkey) and web-based firms (CnYES, Somode and iPartment). Off-line digital content firms tended to adopt ‘resource acquisition strategies’ in their initial stages and ‘marketing strategies’ in second and subsequent stages. In contrast, web-based digital content companies mainly adopted product and marketing strategies in the early stages, and would adopt innovative approaches towards product and marketing strategies in the whole process of their business development. Some web-based digital content companies also adopted organizational restructuring strategies in the final stage. Finally, I propose the ‘Taxonomy Matrix of Entrepreneurial Strategies’ to emphasise the two dimensions of this matrix: innovation, and the firm’s resource acquisition for entrepreneurial strategy. This matrix is divided into four cells: Effective, Bounded, Conservative, and Impoverished.

Information enrichment for quality recommender systems

The explosive growth of the World-Wide-Web and the emergence of ecommerce are the major two factors that have led to the development of recommender systems (Resnick and Varian, 1997). The main task of recommender systems is to learn from users and recommend items (e.g. information, products or books) that match the users’ personal preferences. Recommender systems have been an active research area for more than a decade. Many different techniques and systems with distinct strengths have been developed to generate better quality recommendations. One of the main factors that affect recommenders’ recommendation quality is the amount of information resources that are available to the recommenders. The main feature of the recommender systems is their ability to make personalised recommendations for different individuals. However, for many ecommerce sites, it is difficult for them to obtain sufficient knowledge about their users. Hence, the recommendations they provided to their users are often poor and not personalised. This information insufficiency problem is commonly referred to as the cold-start problem. Most existing research on recommender systems focus on developing techniques to better utilise the available information resources to achieve better recommendation quality. However, while the amount of available data and information remains insufficient, these techniques can only provide limited improvements to the overall recommendation quality. In this thesis, a novel and intuitive approach towards improving recommendation quality and alleviating the cold-start problem is attempted. This approach is enriching the information resources. It can be easily observed that when there is sufficient information and knowledge base to support recommendation making, even the simplest recommender systems can outperform the sophisticated ones with limited information resources. Two possible strategies are suggested in this thesis to achieve the proposed information enrichment for recommenders: • The first strategy suggests that information resources can be enriched by considering other information or data facets. Specifically, a taxonomy-based recommender, Hybrid Taxonomy Recommender (HTR), is presented in this thesis. HTR exploits the relationship between users’ taxonomic preferences and item preferences from the combination of the widely available product taxonomic information and the existing user rating data, and it then utilises this taxonomic preference to item preference relation to generate high quality recommendations. • The second strategy suggests that information resources can be enriched simply by obtaining information resources from other parties. In this thesis, a distributed recommender framework, Ecommerce-oriented Distributed Recommender System (EDRS), is proposed. The proposed EDRS allows multiple recommenders from different parties (i.e. organisations or ecommerce sites) to share recommendations and information resources with each other in order to improve their recommendation quality. Based on the results obtained from the experiments conducted in this thesis, the proposed systems and techniques have achieved great improvement in both making quality recommendations and alleviating the cold-start problem.

Examining the covert nature of product placement : implications for public policy

As consumers become better educated and more skeptical of traditional advertising, alternate forms of marketing communication have emerged that aim to influence audiences unobtrusively. One such example is product placement. Product placement has attracted ongoing debate as to whether it is covert, unethical, and influences consumption. The current article examines the nature and practice of product placement in this light. This taxonomy of product placement attributes is based on current marketing practice and examines whether this is, indeed, a covert marketing strategy. Further, it presents a conceptualization of the influence of product placement on consumer welfare. We highlight that the many forms of product placement necessitate independent evaluation to determine ethical and regulatory standards. Operational solutions for developing public policy are offered.

A Taxonomy of image matching techniques for stereo vision

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Applications of stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics, industrial automation and stereomicroscopy. A key issue in stereo vision is that of image matching, or identifying corresponding points in a stereo pair. The difference in the positions of corresponding points in image coordinates is termed the parallax or disparity. When the orientation of the two cameras is known, corresponding points may be projected back to find the location of the original object point in world coordinates. Matching techniques are typically categorised according to the nature of the matching primitives they use and the matching strategy they employ. This report provides a detailed taxonomy of image matching techniques, including area based, transform based, feature based, phase based, hybrid, relaxation based, dynamic programming and object space methods. A number of area based matching metrics as well as the rank and census transforms were implemented, in order to investigate their suitability for a real-time stereo sensor for mining automation applications. The requirements of this sensor were speed, robustness, and the ability to produce a dense depth map. The Sum of Absolute Differences matching metric was the least computationally expensive; however, this metric was the most sensitive to radiometric distortion. Metrics such as the Zero Mean Sum of Absolute Differences and Normalised Cross Correlation were the most robust to this type of distortion but introduced additional computational complexity. The rank and census transforms were found to be robust to radiometric distortion, in addition to having low computational complexity. They are therefore prime candidates for a matching algorithm for a stereo sensor for real-time mining applications. A number of issues came to light during this investigation which may merit further work. These include devising a means to evaluate and compare disparity results of different matching algorithms, and finding a method of assigning a level of confidence to a match. Another issue of interest is the possibility of statistically combining the results of different matching algorithms, in order to improve robustness.