Search results

In every industry there are resources. Some are moving, others more fixed; some are technical, others social. People working with the resources, for example, as buyers or sellers, or users or producers, may not make much notice of them. A product sells. A facility functions. The business relationship in which we make our money has “always” been there. However, some times this picture of order is disturbed. A user having purchased a product for decades may “suddenly” say to the producer that s/he does not appreciate the product. And a producer having received an order of a product that s/he thought was well known, may find it impossible to sell it. Such disturbances may be ignored. Or they can be used as a platform for development. In this study we investigate the latter option, theoretically and through real world data. Concerning theory we draw on the industrial network approach. We see industrial actors as part of (industrial) networks. In their activities actors use and produce resources. Moreover, the actors interact − bilaterally and multilaterally. This leads to development of resources and networks. Through “thick” descriptions of two cases we illustrate and try to understand the interactive character of resource development and how actors do business on features of resources. The cases are about a certain type of resource, a product − goat milk. The main message to industrial actors is that they should pay attention to that products can be co-created. Successful co-creation of products, moreover, may require development also of business relationships and their connections (“networking”).

This paper deals with the organizing of interactive product development. Developing products in interaction between firms may provide benefits in terms of specialization, increased innovation, and possibilities to perform development activities in parallel. However, the differentiation of product development among a number of firms also implies that various dependencies need to be dealt with across firm boundaries. How dependencies may be dealt with across firms is related to how product development is organized. The purpose of the paper is to explore dependencies and how interactive product development may be organized with regard to these dependencies.

The analytical framework is based on the industrial network approach, and deals with the development of products in terms of adaptation and combination of heterogeneous resources. There are dependencies between resources, that is, they are embedded, implying that no resource can be developed in isolation. The characteristics of and dependencies related to four main categories of resources (products, production facilities, business units and business relationships) provide a basis for analyzing the organizing of interactive product development.

Three in-depth case studies are used to explore the organizing of interactive product development with regard to dependencies. The first two cases are based on the development of the electrical system and the seats for Volvo’s large car platform (P2), performed in interaction with Delphi and Lear respectively. The third case is based on the interaction between Scania and Dayco/DFC Tech for the development of various pipes and hoses for a new truck model.

The analysis is focused on what different dependencies the firms considered and dealt with, and how product development was organized with regard to these dependencies. It is concluded that there is a complex and dynamic pattern of dependencies that reaches far beyond the developed product as well as beyond individual business units. To deal with these dependencies, development may be organized in teams where several business units are represented. This enables interaction between different business units’ resource collections, which is important for resource adaptation as well as for innovation. The delimiting and relating functions of the team boundary are elaborated upon and it is argued that also teams may be regarded as actors. It is also concluded that a modular product structure may entail a modular organization with regard to the teams, though, interaction between business units and teams is needed. A strong connection between the technical structure and the organizational structure is identified and it is concluded that policies regarding the technical structure (e.g. concerning “carry-over”) cannot be separated from the management of the organizational structure (e.g. the supplier structure). The organizing of product development is in itself a complex and dynamic task that needs to be subject to interaction between business units.

The purposes of this paper are to (1) explore how personality traits pertaining to the dominance influence steadiness compliance model manifest themselves in terms of user interaction behavior on social media and (2) examine whether social interaction data on social media platforms can predict user personality.

Social interaction data was collected from 198 users of Sina Weibo, a popular social media platform in China. Their personality traits were also measured via questionnaire. Machine learning techniques were applied to predict the personality traits based on the social interaction data.

The results demonstrated that the proposed classifiers had high prediction accuracy, indicating that our approach is reliable and can be used with social interaction data on social media platforms to predict user personality. “Reposting,” “being reposted,” “commenting” and “being commented on” were found to be the key interaction features that reflected Weibo users' personalities, whereas “liking” was not found to be a key feature.

The findings of this study are expected to enrich personality prediction research based on social media data and to provide insights into the potential of employing social media data for the purpose of personality prediction in the context of the Weibo social media platform in China.

Organizations rely on social outreach campaigns to raise financial support, recruit volunteers, and increase public awareness. In order to maximize response rates, organizations face the challenging problem of designing appropriately tailored interactions for each user. An interaction consists of a specific combination of message, media channel, sender, tone, and possibly many other attributes. The purpose of this paper is to address the problem of how to design tailored interactions for each user to maximize the probability of a desired response.

A nearest-neighbor (NN) algorithm is developed for interaction design. Simulation-based experiments are then conducted to compare positive response rates obtained by two forms of this algorithm against that of several control interaction design strategies. A factorial experimental design is employed which varies three user population factors in a combinatorial manner, allowing the methods to be compared across eight distinct scenarios.

The NN algorithms significantly outperformed all three controls in seven out of the eight scenarios. Increases in response rates ranging from approximately 20 to 400 percent were observed.

This work proposes a data-oriented method for designing tailored interactions for individual users in social outreach campaigns which can enable significant increases in positive response rates. Additionally, the proposed algorithm is relatively easy to implement.

The problem of optimal interaction design in social outreach campaigns is scarcely addressed in the literature. This work proposes an effective and easy to implement solution approach for this problem.

Handling feature interaction is an unsolved issue in feature recognition approach. This paper presents a method for recognizing the presence of feature interactions. First, based on the convex hull concept, a so‐called reference face is defined. Second, by adding the reference face into the attributes adjacency graph (AAG), a modified AAG is obtained. Two general feature types, namely depression and protrusion features, are identified by the reference face. The basic features such as slots, pockets and bosses are represented by the modified AAG. Any features that remain unrecognized by the modified AAG are regarded as interacting features. The types of reference faces and feature face are also classified. Based on the kind of face classification, the interacting features are finally recognized via a process of virtual face extension and volume addition.

Although brands have developed mobile applications (apps) to offer consumers new experiences, low app usage numbers indicate the need to develop a systematic, practical evaluation framework for branded app design that specifies concrete design features.

An expert review provides an overview of the design of current branded apps. On the basis of an extensive literature review, this article classifies state-of-the-art design features for branded apps according to a proposed evaluation framework that includes human–computer interaction (HCI)–related and marketing-related evaluation criteria. In an application of these evaluation criteria, the authors evaluate 73 branded apps issued by 11 top fast-moving consumer goods (FMCG) brands.

The expert review identifies strengths and weaknesses that are common to the design of current branded apps. These findings inform the set of design recommendations that this article offers, which includes 14 features common to all types of apps and 9 features specific to particular types of apps.

This research offers practical implications for app designers, who need to address design dimensions contained in the proposed framework including the HCI-related (mobile, social and user experience design features) and marketing-related (branding and customer relationship management design features) to create effective branded apps.

Design elements identified in prior literature remain abstract and do not prescribe a systematic or pragmatic approach to using them in practice. This study takes a multidisciplinary perspective (HCI, marketing and design science) to establish a practical evaluation framework for branded app designs.

Traditional library book recommendation methods are mainly based on association rules and user profiles. They may help to learn about students' interest in different types of books, e.g., students majoring in science and engineering tend to pay more attention to computer books. Nevertheless, most of them still need to identify users' interests accurately. To solve the problem, the authors propose a novel embedding-driven model called InFo, which refers to users' intrinsic interests and academic preferences to provide personalized library book recommendations.

The authors analyze the characteristics and challenges in real library book recommendations and then propose a method considering feature interactions. Specifically, the authors leverage the attention unit to extract students' preferences for different categories of books from their borrowing history, after which we feed the unit into the Factorization Machine with other context-aware features to learn students' hybrid interests. The authors employ a convolution neural network to extract high-order correlations among feature maps which are obtained by the outer product between feature embeddings.

The authors evaluate the model by conducting experiments on a real-world dataset in one university. The results show that the model outperforms other state-of-the-art methods in terms of two metrics called Recall and NDCG.

It requires a specific data size to prevent overfitting during model training, and the proposed method may face the user/item cold-start challenge.

The embedding-driven book recommendation model could be applied in real libraries to provide valuable recommendations based on readers' preferences.

The proposed method is a practical embedding-driven model that accurately captures diverse user preferences.

The purpose of this paper is to present an approach where a novel user modeling wizard for people with motor impairments is used to gain a deeper understanding of very specific (touch-based and touchless) interaction patterns. The findings are used to set up and fill a user model which allows to automatically derive an application- and user-specific configuration for natural user interfaces.

Based on expert knowledge in the domain of software/user interfaces for people with special needs, a test-case –based user modeling tool was developed. Task-based user tests were conducted with seven users for the touch-based interaction scenario and with five users for the touchless interaction scenario. The participants are all people with different motor and/or cognitive impairments.

The paper describes the results of different test cases that were designed to model users’ touch-based and touchless interaction capabilities. To evaluate the tool’s findings, experts additionally judged the participants’ performance (their opinions were compared to the tool’s findings). The results suggest that the user modeling tool could quite well capture users’ capabilities.

The paper presents a tool that can be used to model users’ interaction capabilities. The approach aims at taking over some of the (very time-consuming) configuration tasks consultants have to do to configure software according to the needs of people with disabilities. This can lead to a wider accessibility of software, especially in the area of gesture-based user interaction.

Part of the approach has been published in the proceedings of the Interactional Conference on Advances in Mobile Computing and Multimedia 2014. Significant additions have been made since (e.g. all of the touchless interaction part of the approach and the related user study).

Rich Internet Application (RIA) technologies offer designers the opportunity to experiment with novel interaction grammars, whose implications for conceptual modeling still need to be fully understood. An open problem is the ability to characterize the fluid, smooth and organic nature of the user interaction and navigation in ways that allow web engineers to share through a common vocabulary, as well as sketch, explore and specify design decisions in the light of usability requirements and stakeholder's goals. The purpose of this paper is to address this problem.

To meet this challenge, the authors extend IDM (Interactive Dialogue Model), a dialogue‐based approach focusing on the conceptual dialogue flow with the user, codifying a set of key modeling constructs in order to describe the new dialogue features of RIAs.

The approach, called Rich‐IDM demonstrated some relevant features: expressiveness to capture interactive features at a high level of abstraction, semi‐formality to facilitate the establishment of a common ground between designers and web engineers, and traceability of the design to important usability requirements.

The paper proposes a simple way to fill the gap between hypermedia design and user experience design for RIAs, which is an open issue, both from the web engineering point of view and the human‐computer interaction point of view.

The authors have described how Rich‐IDM can help designers to capture and cope with some RIA interface flaws. In this case, the benefits of the approach are directly related to the semantics of its primitives.

The authors' proposal is the first, consolidated step of a promising research avenue.

In recent years, knowledge graph completion has gained increasing research focus and shown significant improvements. However, most existing models only use the structures of knowledge graph triples when obtaining the entity and relationship representations. In contrast, the integration of the entity description and the knowledge graph network structure has been ignored. This paper aims to investigate how to leverage both the entity description and the network structure to enhance the knowledge graph completion with a high generalization ability among different datasets.

The authors propose an entity-description augmented knowledge graph completion model (EDA-KGC), which incorporates the entity description and network structure. It consists of three modules, i.e. representation initialization, deep interaction and reasoning. The representation initialization module utilizes entity descriptions to obtain the pre-trained representation of entities. The deep interaction module acquires the features of the deep interaction between entities and relationships. The reasoning component performs matrix manipulations with the deep interaction feature vector and entity representation matrix, thus obtaining the probability distribution of target entities. The authors conduct intensive experiments on the FB15K, WN18, FB15K-237 and WN18RR data sets to validate the effect of the proposed model.

The experiments demonstrate that the proposed model outperforms the traditional structure-based knowledge graph completion model and the entity-description-enhanced knowledge graph completion model. The experiments also suggest that the model has greater feasibility in different scenarios such as sparse data, dynamic entities and limited training epochs. The study shows that the integration of entity description and network structure can significantly increase the effect of the knowledge graph completion task.

The research has a significant reference for completing the missing information in the knowledge graph and improving the application effect of the knowledge graph in information retrieval, question answering and other fields.