Keyword-based Method Research Articles

Complexity Theory Approach to Innovation Ecosystems

Purpose: By nowadays, in addition to the innovation systems definitions, the research area of innovation ecosystems operation is also developing significantly. The aim of the research is to examine how the concept of the innovation ecosystem and the conceptual scope of complexity theory are related. Theoretical reference: The paper gives an overview of development of innovation ecosystems literature, and also introduces summary of general systems theory. The authors point out that the joint discussion of the two areas are very rare in the related research works. There are few examples of referring Complex Adaptive Systems as potential approach for innovation ecosystems, but detailed theoretical analysis of the topic is limited. Method: The paper analyses the relationship and possible overlap of fields of innovation ecosystems and complexity theory by evaluation of findings of content analysis and a keyword-based method. As part of the methodology presented, the research of the theme is carried out from two aspects. First, based on review-type and theoretical works, a content analysis was made to define specific key feature word sets in both innovation ecosystems and complex theory areas. Then, based on these keyword set, validation was executed based on abstracts of selected papers in order to define possible relations of the two fields. Results and Conclusion: As a result of the research, authors draw conclusions about the relationship between the definition of innovation ecosystems and complexity theory. Both the joint keywords and the non-relevant words have been pointed out. The authors concluded that there is apparent theoretical relation of the two areas from content point of view, based on analysis of relevant scientific papers. Implications of research: The outcomes of the research fundamentally influence the treatment of innovation ecosystems, which has been traditionally assumed linear, deterministic and controllable behaviour. Introducing the potential of complex systems allow opening new aspects to manage such challenges of innovation ecosystems which could not been handled in the usual way. Originality/value: The joint discussion of the topic of innovation ecosystems and complex systems theory is rather rare in the related scientific works. The novelty of the current paper is the systematic approach defined for this analysis purpose and way of validation of the pre-defined keyword set through abstracts of relevant papers. The present research addressed the preliminary discussion of the given research question, further research and analysis can be made based on larger-scale paper base.

Detecting Arabic Spam Reviews in Social Networks Based on Classification Algorithms

Reviews or comments that users leave on social media have great importance for companies and business entities. New product ideas can be evaluated based on customer reactions. However, this use of social media is complicated by those who post spam on social media in the form of reviews and comments. Designing methodologies to automatically detect and block social media spam is complicated by the fact that spammers continuously develop new ways to leave their spam comments. Researchers have proposed several methods to detect English spam reviews. However, few studies have been conducted to detect Arabic spam reviews. This article proposes a keyword-based method for detecting Arabic spam reviews. Keywords or Features are subsets of words from the original text that are labelled as important. A term's weight, Term Frequency–Inverse Document Frequency (TF-IDF) matrix, and filter methods (such as information gain, chi-squared, deviation, correlation, and uncertainty) have been used to extract keywords from Arabic text. The method proposed in this article detects Arabic spam in Facebook comments. The dataset consists of 3,000 Arabic comments extracted from Facebook pages. Four different machine learning algorithms are used in the detection process, including C4.5, kNN, SVM, and Naïve Bayes classifiers. The results show that the Decision Tree classifier outperforms the other classification algorithms, with a detection accuracy of 92.63%.

Structuring electronic dental records through deep learning for a clinical decision support system.

Extracting information from unstructured clinical text is a fundamental and challenging task in medical informatics. Our study aims to construct a natural language processing (NLP) workflow to extract information from Chinese electronic dental records (EDRs) for clinical decision support systems (CDSSs). We extracted attributes, attribute values, and tooth positions based on an existing ontology from EDRs. A workflow integrating deep learning with keywords was constructed, in which vectors representing texts were unsupervised learned. Specifically, we implemented Sentence2vec to learn sentence vectors and Word2vec to learn word vectors. For attribute recognition, we calculated similarity values among sentence vectors and extracted attributes based on our selection strategy. For attribute value recognition, we expanded the keyword database by calculating similarity values among word vectors to select keywords. Performance of our workflow with the hybrid method was evaluated and compared with keyword-based method and deep learning method. In both attribute and value recognition, the hybrid method outperforms the other two methods in achieving high precision (0.94, 0.94), recall (0.74, 0.82), and F score (0.83, 0.88). Our NLP workflow can efficiently structure narrative text from EDRs, providing accurate input information and a solid foundation for further data-based CDSSs.

QoS-Based Collaborative Filtering for Web Service Mining

Stored information in the databases is heterogeneous, from various sources, and of large volumes. The web service selection becomes nontrivial, as the users are easily overloaded by vast amount candidates. Using the keyword-based search method, users are struggling to choose the best web services among those having similar features. In the traditional methods, the users set different constraints and QoS parameters of a web service from what's claimed by the provider. Moreover, different researches challenge this problem, introducing semantic discovery process to enable relevant and desired search results. These approaches don't give importance to users' opinions and the selection history. The classical development of the ontology is typically entirely based on high human participation. In this paper, the authors use ontology-based querying, user profile to know the history, new collaborative filtering to calculate user, and query similarity and QoS as the final step for web service selection. The approach combines the syntactic and semantic methods to increase the selection precision.

A DISCOURSE-BASED INFORMATION RETRIEVAL FOR TAMIL LITERARY TEXTS

Tamil literature has many valuable thoughts that can help the human community to lead a successful and a happy life. Tamil literary works are abundantly available and searched on the World Wide Web (WWW), but the existing search systems follow a keyword-based match strategy which fails to satisfy the user needs. This necessitates the demand for a focused Information Retrieval System that semantically analyses the Tamil literary text which will eventually improve the search system performance. This paper proposes a novel Information Retrieval framework that uses discourse processing techniques which aids in semantic analysis and representation of the Tamil Literary text. The proposed framework has been tested using two ancient literary works, the Thirukkural and Naladiyar, which were written during 300 BCE. The Thirukkural comprises 1330 couplets, each 7 words long, while the Naladiyar consists of 400 quatrains, each 15 words long. The proposed system, tested with all the 1330 Thirukkural couplets and 400 Naladiyar quatrains, achieved a mean average precision (MAP) score of 89%. The performance of the proposed framework has been compared with Google Tamil search and a keyword-based search which is a substandard version of the proposed framework. Google Tamil search achieved a MAP score of 56% and keyword-based method achieved a MAP score of 62% which shows that the discourse processing techniques improves the search performance of an Information Retrieval system.

Multidimensional Semantic Scan for Pre-Syndromic Disease Surveillance

Multidimensional Semantic Scan for Pre-Syndromic Disease Surveillance

O ONTOLOGY-BASED PARAGRAPH EXTRACTION AND CAUSALITY DETECTION-BASED SIMILARITY FOR ANSWERING WHY-QUESTION

Paragraph extraction is a main part of an automatic question answering system, especially in answering why-question. It is because the answer of a why-question usually contained in one paragraph instead of one or two sentences. There have been some researches on paragraph extraction approaches, but there are still few studies focusing on involving the domain ontology as a knowledge base. Most of the paragraph extraction studies used keyword-based method with small portion of semantic approaches. Thus, the question answering system faces a typical problem often occuring in keyword-based method that is word mismatches problem. The main contribution of this research is a paragraph scoring method that incorporates the TFIDF-based and causality-detection-based similarity. This research is a part of the ontology-based why-question answering method, where ontology is used as a knowledge base for each steps of the method including indexing, question analyzing, document retrieval, and paragraph extraction/selection. For measuring the method performance, the evaluations were conducted by comparing the proposed method over two baselines methods that did not use causality-detection-based similarity. The proposed method shown improvements over the baseline methods regarding MRR (95%, 0.82-0.42), P@1 (105%, 0.78-0.38), P@5(91%, 0.88-0.46), Precision (95%, 0.80-0.41), and Recall (66%, 0.88-0.53).

Automatic summarization of medical interviews

Abstract. The genomic-based targeted therapy (Crizotinib) has been emerged as an alternative option for the treatment of patients with locally advanced or metastatic non-small cell lung cancer, comprising the 85\% of lung cancer. However, Crizotinib is not listed in VA drug formulary- and is not available for VA oncologists to treat lung cancer currently. Therefore, for understanding physicians’ views on using genomic services, semi-structured interviews were collected. In this paper, we will present an innovative method to extract summarization from medical interviews automatically. Different from keyword-based method, automatic summarization can help to understand the intention of physicians. Compared with the existing summarization methods, our work is based on latent Dirichlet allocation and recent results m word embeddings that learn seinantically meaningful representations for words from local cooccurrences in sentences. Experiments on medical interviews demonstrate that the proposed algorithm achieves good results compared with a gold standard file using manual extraction technique.

A keyword-based mining method for customer segmentation

A keyword-based mining method for customer segmentation

Face Retrieval Using Image Moments and Genetic Algorithm

Content-based image retrieval has been developed in numerous fields. This provides more active management and retrieval of images than the keyword-based method. So the content based image retrieval becomes one of the liveliest researches in the past few years.In a given set of objects, the retrieval of information suggests solutions to search forthose in response to a particular description. The set of objects which can be considered are documents,images, videos, or sounds. Moments can be viewed as powerful image descriptors that capture global characteristics of an image. The magnitude of the moment coefficients is said to be invariant under geometrical transformations like rotation which makes them suitable for most of the recognition applications. This paper presents a method to retrieve a multi-view face from a large face database according to face image moments and genetic algorithm. The GA is preferred for its power and because it can be usedwithout any specificinformation of the domain. The experimental results concludes thatusing GA gives a good performance and it decreases the average search time to (56.44milliseconds) compared with (891.6 milliseconds) for traditional search.

Library and Information Science Research in China—A Survey Based Analysis of 10 LIS Educational Institutes

This paper aims to conduct a quantitative evaluation on the achievement, research productivity, and research hotspots of “Library, Information and Archives management” Science schools or departments in China. In this paper, the “LIS” in China is firstly defined. Before evaluation, data are collected from CSSCI (Chinese Social Science Citation Index)-indexed papers and SSCI (Social Science Citation Index)-indexed papers, as well as projects granted by the two authoritative national foundations in China, SSFC (National Social Science Foundation of China) and NSFC (National Natural Science Foundation of China). Then, a bibliometric-based method and a keyword-based method are employed to analyze the collected data from different perspectives, including annual distribution, author productivity, institute productivity and influence. Through the analysis, several conclusions are made: a) collaborative groups exist, though no particular collaboration preference is exhibited. b) Interdisciplinary research promotes the emergence of new disciplines. c) There are four top institutes with outstanding productivity and six hot research topics in the “LIS” study in China. Also, in a five-year period, “LIS” scholars have paid much attention on network technology and its application in this field. Research addressing the view of “information” is much more popular than the ubiquitous conception of “library”. d) There still exist some issues in China's LIS research, for example, the unbalanced development of educational institutes, the excessive preference of theoretical research over technical research, etc.

Keyword-based mobile semantic search using mobile ontology

A large volume of mobile data is being generated and shared among mobile devices such as smartphones. Most of the mobile platforms provide a user with a keyword-based full text search (FTS) in order to search for mobile data. However, FTS only returns the data corresponding to the keywords given by users as results without considering a user’s query intention. To overcome this limitation, we propose a semantically enhanced keyword-based search method. Although there are various semantic search techniques, it is hard to apply existing methods to mobile devices just as they are. This is caused by the characteristics of mobile devices such as isolated database structures and limited computing resources. To enable semantic search on mobile devices, we also propose a lightweight mobile ontology. Experimental results from the prototype implementation of the proposed method show that the proposed method provides a better user experience than the conventional FTS and returns accurate search results in an acceptable response time.

Building a semantic based public transportation geoportal compliant with the INSPIRE transport network data theme

Interoperability is becoming essential for the today’s geographic information systems. Geographic information is usually available as datasets stored in databases and accessible via GIS. However, these information sources are increasingly heterogeneous and show differences in data formats, database schema and object concepts. To satisfy the increased demand for the use and sharing of geographic data in common applications, considering the heterogeneity and the methods to support interoperability are required by the GIS community. The implementation of Spatial Data Infrastructure (SDI) such as the European INSPIRE (Infrastructure for Spatial Information in the European Community) enables accessibility and the sharing of geographic data and interoperability among the systems. In addition to this, traditional GIS systems perform spatial queries using a keyword-based method. However, this approach remains incapable of fully expressing the users' needs due to a lack of geographic concepts (semantics) in the dataset. Different terms may refer to similar concepts, while the same terms may refer to different concepts. This causes semantic heterogeneity in the dataset. In this context, the most promising approach is the implementation of geospatial semantics by means of ontology in the geospatial dataset to overcome this kind of ambiguity. The aim of this research is to investigate the implementation of INSPIRE as a SDI standard and the use of Semantic Technology to empower the traditional GIS approach. In this regard, a public transportation geoportal has been developed for the experimental investigation which uses a revised sample transportation data complaint with the INSPIRE Transport Network Data Theme and a developed Transportation Ontology Domain, including concepts, relationships and individuals to provide a semantic spatial search.

음향학적 자질을 활용한 비디오 스피치 요약의 자동 추출과 표현에 관한 연구

스피치 요약을 생성하는데 있어서 두 가지 중요한 측면은 스피치에서 핵심 내용을 추출하는 것과 추출한 내용을 효과적으로 표현하는 것이다. 본 연구는 강의 자료의 스피치 요약의 자동 생성을 위해서 스피치 자막이 없는 경우에도 적용할 수 있는 스피치의 음향학적 자질 즉, 스피치의 속도, 피치(소리의 높낮이) 및 강도(소리의 세기)의 세 가지 요인을 이용하여 스피치 요약을 생성할 수 있는지 분석하고, 이 중 가장 효율적으로 이용할 수 있는 요인이 무엇인지 조사하였다. 조사 결과, 강도(최대값 dB과 최소값 dB간의 차이)가 가장 효율적인 요인으로 확인되었다. 이러한 강도를 이용한 방식의 효율성과 특성을 조사하기 위해서 이 방식과 본문 키워드 방식간의 차이를 요약문의 품질 측면에서 분석하고, 이 두 방식에 의해서 각 세그먼트(문장)에 할당된 가중치간의 관계를 분석해 보았다. 그런 다음 추출된 스피치의 핵심 세그먼트를 오디오 또는 텍스트 형태로 표현했을 때 어떤 특성이 있는지 이용자 관점에서 분석해 봄으로써 음향학적 특성을 이용한 스피치 요약을 효율적으로 추출하여 표현하는 방안을 제안하였다.

A New E-Government Service Discovery Method based on Similarity

With the development of the E-Government, government portal has integrated a great deal of service information. The traditional methods of service discovery can not meet the diverse needs of users. Based on the current research, this paper proposed a new similarity-based method for e-government service discovery. The current static service workflows are re-combined to make them dynamic and more flexible. Then the most appropriate service is recommended to users by matching all similar services with users’ demands. It shows the web services of government portal are more intelligent and personalized. Experiments show that the method has more advantages than keyword-based method or ontology-based method.

Keyword-Based Deep Web Database Selection

This paper proposes a keyword-based Deep Web search method: Given keyword queries provided by users,the proposed method on-the-fly selects the databases capturing the queryintent and providing high-quality data.The method,which is much more efficient than Deep Webcrawling,can support keyword search over multiple-domain Deep Web databases,and thus can besmoothly integrated with the existing search engine architecture.In this paper,we focus on key-word-based Deep Web database selection,and studythe research challenges that naturally arisein the proposed method.(1) We introduce an effective model to measure the relevance of database-domain attributes with respect to keyword queries,and propose a random-walk algorithm to compute the relevance fromdatabase query logs.(2) We develop a novel database sampling method for measuring the relevance of databases with respect to queries,in order to select relevant data-bases in the selected domains.We have implemented our methods on real data sets fromthe Chinese Deep Web.The experi mental results show that our methods achieve high effectiveness.

A Semantic Matchmaker for Ranking Web Services

This paper is concerned with the matchmaker for ranking web services by using semantics. So far several methods of semantic matchmaker have been proposed. Most of them, however, focus on classifying the services into predefined categories rather than providing a ranking result. In this paper, a new method of semantic matchmaker is proposed for ranking web services. It is proposed to use the semantic distance for estimating the matching degree between a service and a user request. Four types of semantic distances are defined and four algorithms are implemented respectively to calculate them. Experimental results show that the proposed semantic matchmaker significantly outperforms the keyword-based baseline method.

Beyond keyword and cue-phrase matching: A sentence-based abstraction technique for information extraction

With the explosion in the quantity of on-line text and multimedia information in recent years, there has been a renewed interest in the automated extraction of knowledge and information in various disciplines. In this paper, we provide a novel quantitative model for the creation of a summary by extracting a set of sentences that represent the most salient content of a text. The model is based on a shallow linguistic extraction technique. What distinguishes it from previous research is that it does not work on the detection of specific keywords or cue-phrases to evaluate the relevance of the sentence concerned. Instead, the attention is focused on the identification of the main factors in the textual continuity. Simulation experiments suggest that this technique is useful because it moves away from a purely keyword-based method of textual information extraction and its associated limitations.

시멘틱 웹 기반 DQL 검색 시스템 설계

It has been proposed diverse methods to use web information efficiently as the size of information is increasing. Most of search systems use a keyword-based method that mostly relies on syntactic information. They cannot utilize semantic information of documents and thus they could generate to users. To solve shortcoming in searching documents, a technique using the Semantic Web is suggested. A semantic web can find relevant information to users by employing metadata which are represented using standard ontologies. Each document is annotated with a metadata which can be reasoned by agents. In this paper, we propose a search system using semantic web technologies. Our semantic search system analyzes semantically questions that user input, and get resolution information that user want. To improve efficiency and accuracy of semantic search systems, this paper proposes DQL(DAML Query Language) engine that employs inference engine to execute reasoning and DQL converter that changes keyword form question of the user to DQL.

Automatic Indexing of Lecture Presentations Using Unsupervised Learning of Presumed Discourse Markers

A new method for automatic detection of section boundaries and extraction of key sentences from lecture audio archives is proposed. The method makes use of 'discourse markers' (DMs), which are characteristic expressions used in initial utterances of sections, together with pause and language model information. The DMs are derived in a totally unsupervised manner based on word statistics. An experimental evaluation using the Corpus of Spontaneous Japanese (CSJ) demonstrates that the proposed method provides better indexing of section boundaries compared with a simple baseline method using pause information only, and that it is robust against speech recognition errors. The method is also applied to extraction of key sentences that can index the section topics. The statistics of the presumed DMs are used to define the importance of sentences, which favors potentially section-initial ones. The measure is also combined with the conventional tf-idf measure based on content words. Experimental results confirm the effectiveness of using the DMs in combination with the keyword-based method. The paper also describes a statistical framework for transforming raw speech transcriptions into the document style for defining appropriate sentence units and improving readability.