Search results

The purpose of this paper is to propose a solution to the problem of a lack of machine processable semantics in business process management.

The paper introduces a methodology that combines domain and company‐specific ontologies and databases to obtain multiple levels of abstraction for process mining and analysis. The authors valuated this approach with a real case study from the apparel domain, using a prototype system and techniques developed in the Process Mining Framework (ProM). The results of this approach are compared with similar research.

Semantically enriching process execution data can successfully raise analysis from the syntactic to the semantic level, and enable multiple perspectives of analysis on business processes. Combining this approach with complementary research in semantic business process management (SBPM) can provide results comparable to multidimensional analysis in data warehouse and on line analytical processing (OLAP) technologies.

The approach and prototype described in this paper improve the richness of semantics available for open‐source process mining and analysis tools like ProM, and the richness and detail of the resulting analysis.

The purpose of this paper is to explore the orientations of collaborative networks (CNs) for managing integrated information flow. It seeks to analyse and shed light into the main priorities of firms for sharing and coordinating information with CN partners. These priorities are needed to enhance practices to trade-off and integrate flows where appropriate for maximising profits and performance.

In this study, inductive multiple-case logic is applied to research how six industrial firms manage integrated information flow in relation to their collaborative networked organisations (CNOs). Guided by an interpretivism epistemology, 22 face-to-face and 13 telephonic semi-structured interviews were conducted with 14 key informants in six industrial firms. Interview data were analysed in line with the research agenda to understand orientations for integrated information flow.

The research finds that CN management is enhanced when flow integration for industrial firms is skill, project, agreement and relationship oriented. The investigation also finds that CNO flow integration could be enhanced when industrial firms confront and prioritise schemes for fluidity prevention, systematised templates, procedural prompts, implementation checklists, confidence building, issuance policies and concern separation.

The major contribution of this paper is an exposition on priorities for integrated information flow within CNs. It also offers insights that suggest industrial firms can boost the performance of their CNOs by: working in small knit highly skilled teams, tactically implementing manufacturability and marketability programmes, strategising their production contracts and strengthening their company-customer-supplier ties.

Drawing on the pleasure-arousal-dominance (PAD) emotion model, the emotional states of consumers embedded in online reviews can be described through three dimensions, that is, pleasure, arousal and dominance, rather than only the one-dimensional positive and negative polarity, as in previous studies. Therefore, this study aims to explore the effect of online review emotion on perceived review helpfulness based on these three basic emotional dimensions.

A lexicon-based method is developed to analyze PAD emotions of online reviews from JD.com. The zero-inflated negative binomial regression is utilized to empirically validate the study hypothesis. The authors examine the influence of pleasure, arousal, dominance, emotion diversity and emotion deviation on review helpfulness, as well as the moderating effect of product type on the relationship between all independent variables and online review helpfulness.

The study results show that the pleasure emotion impairs the helpfulness of online reviews, while the arousal and dominance emotions have a positive impact. Moreover, the authors find that compared with search products, the effects of pleasure, arousal and dominance on perceived helpfulness are strengthened for experience products. However, the emotional diversity and emotional deviation have opposite effects on the helpfulness of search products and experience products. Additionally, the results show that dominance emotion plays a more important role in the interaction effect.

The empirical findings confirm the applicability of PAD in the online review context and extend the existing knowledge of the influence of review emotion on helpfulness. A feasible scheme for extracting PAD variables from Chinese text is developed. The study findings also have significant implications for reviewers, merchants and platform managers of e-commerce websites.

Despite a significant focus on customer evaluation and sentiment analysis, limited attention has been paid to discrete emotional perspective in terms of the emotionality used in text. This paper aims to extend the general-sentiment dictionary in Chinese to a restaurant-domain-specific dictionary, visualize spatiotemporal sentiment trends, identify the main discrete emotions that affect customers’ ratings in a restaurant setting and identify constituents of influential emotions.

A total of 683,610 online restaurant reviews downloaded from Dianping.com were analyzed by a sentiment dictionary optimized by the authors; the main emotions (joy, love, trust, anger, sadness and surprise) that affect online ratings were explored by using multiple linear regression methods. After tracking these sentiment review texts, Latent Dirichlet Allocation (LDA) and LDA models with term frequency-inverse document frequency as weights were used to find the factors that constitute influential emotions.

The results show that it is viable to optimize or expand sentiment dictionary by word similarity. The findings highlight that love and anger have the highest effect on online ratings. The main factors that constitute consumers’ anger (local characteristics, incorrect food portions and unobtrusive location) and love (comfortable dining atmosphere, obvious local characteristics and complete supporting services) are identified. Different from previous studies, negativity bias is not observed, which poses a question of whether it has to do with Chinese culture.

These findings can help managers monitor the true quality of restaurant service in an area on time. Based on the results, restaurant operators can better decide which aspects they should pay more attention to; platforms can operate better and can have more manageable webpage settings; and consumers can easily capture the quality of restaurants to make better purchase decisions.

This study builds upon the existing general sentiment dictionary in Chinese and, to the best of the authors’ knowledge, is the first to provide a restaurant-domain-specific sentiment dictionary and use it for analysis. It also reveals the constituents of two prominent emotions (love and anger) in the case of restaurant reviews.

The purpose of this paper is to improve the conceptual-based search by incorporating structural ontological information such as concepts and relations. Generally, Semantic-based information retrieval aims to identify relevant information based on the meanings of the query terms or on the context of the terms and the performance of semantic information retrieval is carried out through standard measures-precision and recall. Higher precision leads to the (meaningful) relevant documents obtained and lower recall leads to the less coverage of the concepts.

In this paper, the authors enhance the existing ontology-based indexing proposed by Kohler et al., by incorporating sibling information to the index. The index designed by Kohler et al., contains only super and sub-concepts from the ontology. In addition, in our approach, we focus on two tasks; query expansion and ranking of the expanded queries, to improve the efficiency of the ontology-based search. The aforementioned tasks make use of ontological concepts, and relations existing between those concepts so as to obtain semantically more relevant search results for a given query.

The proposed ontology-based indexing technique is investigated by analysing the coverage of concepts that are being populated in the index. Here, we introduce a new measure called index enhancement measure, to estimate the coverage of ontological concepts being indexed. We have evaluated the ontology-based search for the tourism domain with the tourism documents and tourism-specific ontology. The comparison of search results based on the use of ontology “with and without query expansion” is examined to estimate the efficiency of the proposed query expansion task. The ranking is compared with the ORank system to evaluate the performance of our ontology-based search. From these analyses, the ontology-based search results shows better recall when compared to the other concept-based search systems. The mean average precision of the ontology-based search is found to be 0.79 and the recall is found to be 0.65, the ORank system has the mean average precision of 0.62 and the recall is found to be 0.51, while the concept-based search has the mean average precision of 0.56 and the recall is found to be 0.42.

When the concept is not present in the domain-specific ontology, the concept cannot be indexed. When the given query term is not available in the ontology then the term-based results are retrieved.

In addition to super and sub-concepts, we incorporate the concepts present in same level (siblings) to the ontological index. The structural information from the ontology is determined for the query expansion. The ranking of the documents depends on the type of the query (single concept query, multiple concept queries and concept with relation queries) and the ontological relations that exists in the query and the documents. With this ontological structural information, the search results showed us better coverage of concepts with respect to the query.

With the rapid development of digital information and modelling software applications for construction, questions have arisen about their impact on construction safety. Meanwhile, recognition that designers can help reduce risks involved in construction, operation and maintenance via a prevention through design (PtD) approach (also known as design for safety) highlights the significance of digital technologies and tools to PtD. Thus, this paper aims to provide a systematic review of a wide range of digital technologies for enhancing PtD.

A five-stage systematic literature review with coding and synthesis of findings is presented. The review covers journal articles published between 2000 and 2020 related to the applications of various digital technologies, such as building information modelling (BIM), 4D, databases, ontologies, serious games, virtual reality and augmented reality, for addressing safety issues during the design phase in construction.

Analysis of the articles yielded a categorisation of the digital applications for PtD into four main areas: knowledge-based systems; automatic rule checking; hazard visualization; and safety training for designers. The review also highlighted designers’ limited knowledge towards construction safety and the possibility to address this by using gaming environments for educating designers on safety management and using artificial intelligence for predicting hazards and risks during design stage in a BIM environment. Additionally, the review proposes other directions for future research to enhance the use of digital technologies for PtD.

This paper contextualises current digital technology applications for construction health and safety and enables future directions of research in the field to be identified and mapped out.

DBpedia extracts structured information from Wikipedia, interlinks it with other knowledge bases and freely publishes the results on the web using Linked Data and SPARQL. However, the DBpedia release process is heavyweight and releases are sometimes based on several months old data. DBpedia‐Live solves this problem by providing a live synchronization method based on the update stream of Wikipedia. This paper seeks to address these issues.

Wikipedia provides DBpedia with a continuous stream of updates, i.e. a stream of articles, which were recently updated. DBpedia‐Live processes that stream on the fly to obtain RDF data and stores the extracted data back to DBpedia. DBpedia‐Live publishes the newly added/deleted triples in files, in order to enable synchronization between the DBpedia endpoint and other DBpedia mirrors.

During the realization of DBpedia‐Live the authors learned that it is crucial to process Wikipedia updates in a priority queue. Recently‐updated Wikipedia articles should have the highest priority, over mapping‐changes and unmodified pages. An overall finding is that there are plenty of opportunities arising from the emerging Web of Data for librarians.

DBpedia had and has a great effect on the Web of Data and became a crystallization point for it. Many companies and researchers use DBpedia and its public services to improve their applications and research approaches. The DBpedia‐Live framework improves DBpedia further by timely synchronizing it with Wikipedia, which is relevant for many use cases requiring up‐to‐date information.

The new DBpedia‐Live framework adds new features to the old DBpedia‐Live framework, e.g. abstract extraction, ontology changes, and changesets publication.

This study aims to establish a model for rapid and accurate emotion recognition in restaurant online reviews, thus advancing the literature and providing practical insights into electronic word-of-mouth management for the industry.

This study elaborates a hybrid model that integrates deep learning (DL) and a sentiment lexicon (SL) and compares it to five other models, including SL, random forest (RF), naïve Bayes, support vector machine (SVM) and a DL model, for the task of emotion recognition in restaurant online reviews. These models are trained and tested using 652,348 online reviews from 548 restaurants.

The hybrid approach performs well for valence-based emotion and discrete emotion recognition and is highly applicable for mining online reviews in a restaurant setting. The performances of SL and RF are inferior when it comes to recognizing discrete emotions. The DL method and SVM can perform satisfactorily in the valence-based emotion recognition.

These findings provide methodological and theoretical implications; thus, they advance the current state of knowledge on emotion recognition in restaurant online reviews. The results also provide practical insights into intelligent service quality monitoring and electronic word-of-mouth management for the industry.

This study proposes a superior model for emotion recognition in restaurant online reviews. The methodological framework and steps are elucidated in detail for future research and practical application. This study also details the performances of other commonly used models to support the selection of methods in research and practical applications.

Enterprise knowledge graphs (EKG) in resource description framework (RDF) consolidate and semantically integrate heterogeneous data sources into a comprehensive dataspace. However, to make an external relational data source accessible through an EKG, an RDF view of the underlying relational database, called an RDB2RDF view, must be created. The RDB2RDF view should be materialized in situations where live access to the data source is not possible, or the data source imposes restrictions on the type of query forms and the number of results. In this case, a mechanism for maintaining the materialized view data up-to-date is also required. The purpose of this paper is to address the problem of the efficient maintenance of externally materialized RDB2RDF views.

This paper proposes a formal framework for the incremental maintenance of externally materialized RDB2RDF views, in which the server computes and publishes changesets, indicating the difference between the two states of the view. The EKG system can then download the changesets and synchronize the externally materialized view. The changesets are computed based solely on the update and the source database state and require no access to the content of the view.

The central result of this paper shows that changesets computed according to the formal framework correctly maintain the externally materialized RDB2RDF view. The experiments indicate that the proposed strategy supports live synchronization of large RDB2RDF views and that the time taken to compute the changesets with the proposed approach was almost three orders of magnitude smaller than partial rematerialization and three orders of magnitude smaller than full rematerialization.

The main idea that differentiates the proposed approach from previous work on incremental view maintenance is to explore the object-preserving property of typical RDB2RDF views so that the solution can deal with views with duplicates. The algorithms for the incremental maintenance of relational views with duplicates published in the literature require querying the materialized view data to precisely compute the changesets. By contrast, the approach proposed in this paper requires no access to view data. This is important when the view is maintained externally, because accessing a remote data source may be too slow.

Large collections of patent documents disclosing novel, non-obvious technologies are publicly available and beneficial to academia and industries. To maximally exploit its potential, searching these patent documents has increasingly become an important topic. Although much research has processed a large size of collections, a few studies have attempted to integrate both patent classifications and specifications for analyzing user queries. Consequently, the queries are often insufficiently analyzed for improving the accuracy of search results. This paper aims to address such limitation by exploiting semantic relationships between patent contents and their classification.

The contributions are fourfold. First, the authors enhance similarity measurement between two short sentences and make it 20 per cent more accurate. Second, the Graph-embedded Tree ontology is enriched by integrating both patent documents and classification scheme. Third, the ontology does not rely on rule-based method or text matching; instead, an heuristic meaning comparison to extract semantic relationships between concepts is applied. Finally, the patent search approach uses the ontology effectively with the results sorted based on their most common order.

The experiment on searching for 600 patent documents in the field of Logistics brings better 15 per cent in terms of F-Measure when compared with traditional approaches.

The research, however, still requires improvement in which the terms and phrases extracted by Noun and Noun phrases making less sense in some aspect and thus might not result in high accuracy. The large collection of extracted relationships could be further optimized for its conciseness. In addition, parallel processing such as Map-Reduce could be further used to improve the search processing performance.

The experimental results could be used for scientists and technologists to search for novel, non-obvious technologies in the patents.

High quality of patent search results will reduce the patent infringement.

The proposed ontology is semantically enriched by integrating both patent documents and their classification. This ontology facilitates the analysis of the user queries for enhancing the accuracy of the patent search results.