جستجوی مقالات مرتبط با کلیدواژه « متن کاوی » در نشریات گروه « کتابداری و مدیریت اطلاعات »

Following recent trends in information management systems, conventional word-based information retrieval methods are changing to concept-based approaches by means of the broad application of ontologies. More specifically, the use of ontologies for knowledge management is significant in the medical sciences and human disease domains due to the diversity and necessity of information sharing between numerous data repositories such as medical records, health record systems, and so on. Furthermore, ontologies make natural language processing approaches more feasible by reducing semantic ambiguity and making concepts comprehensible to computer-based deductions. In this research, a semi-automated approach for ontology development is proposed, which assists in identifying structural components of an ontology and determining possible relations between them based on scientific text records. The proposed approach, in a general view, includes the gathering of a large volume of technical data in text format, processing, and extraction of results with a minimal contribution of human-based supervision. The processing stage is coded in Matlab code named TmbOnt_Alfa and applies two main techniques including word frequency and Lexico-Synactic patterns analysis, to identify concepts and relations, respectively. The role of the human supervisor is narrowed to entering target terms, eliminating unnecessary outputs, and finalizing the ontology structure. In order to evaluate the efficiency of the proposed method, a case study for ontological development in the field of glaucoma has been conducted, and results are compared with medical subject headings of MESH descriptors, the Persian medical thesaurus, ontology of diseases, and Bioassay ontology (BAO).According to results, the developed ontology, when compared by Glaucoma entry, covered 80% of the medical titles in Mesh, 100% of the medical terms developed in the Persian Medical Thesaurus, and 100% of the Persian medical descriptors. Moreover, the resultant ontology structure is compatible with more than 90% of the same ontology represented in Bioassay and 57% of the ontology of diseases (DO). It also proposed an average of 30% more terms for existing ontological structures.

Considering the role of studying the thematic trend of knowledge and information science research in showing the weaknesses, shortcomings and the path of progress and development of that field, the present study intends to study the topics of articles conducted by Iranian researchers at the national and international levels in this field.

The present study is applied and has been done with the approach of text mining and automated classification analysis. The study population includes articles extracted from the website of Iranian journals indexed in the ISC database during 1977-2019, and the articles done by Iranian researchers that have been indexed in the Web of Science website from 2019-1945. All preprocessing and classification processes are implemented in the Python programming language.

In order to categorize the studies of knowledge and information science, by examining the study backgrounds and combining the existing classifications and consulting experts in this field, a plan consisting of 31 subject areas was prepared and based on the analysis. The findings showed that most of the researches in this field are focused on libraries and information centers and archives; respectively; Research, study and publication; Scientometrics and informatics; and Internet and web studies. In contrast, areas of artificial intelligence; Semantic and ontological web; Information and knowledge-based society; and information systems have the least amount of research. An examination of the concepts and vocabulary used in the studies of this field showed that the word "library" in Iranian articles is the most frequent concept among other concepts in this period. Other commonly used concepts in this course include: Information, University, Science, Study, Knowledge, Management, Evaluation, Web, Library, Technology, Services, and Librarians. Among co-occurrence terms, the terms university library, public library, knowledge management, information science, information retrieval behavior, information technology, medical sciences, national library, digital library, central library, and information retrieval were among the most commonly used terms. Common use of terms such as knowledge, management, technology, knowledge management and information technology, digital, digital library, social network, information literacy, cloud computing and e-government shows the increasing attention of Iranian researchers to interdisciplinary and technology-based topics. Concepts and topics of Iranian research, especially in recent years, have undergone changes in various economic, social and cultural dimensions under the influence of web development and the development of semantic technologies, smart tools, globalization and advances in communication, and comprehensive development.

The results of the present study can help in planning and decision-making regarding recognizing educational and research needs, formulating curricula, and guiding future scientific outputs towards priorities and optimal allocation of resources to them. These results can also guide researchers in deciding to select future research topics in knowledge and information science.

Keyword extraction is one of the most important issues in text processing and analysis and provides a high-level and accurate summary of the text. Therefore, choosing the right method to extract keywords from the text is important. The aim of the present study was to compare the performance of three approaches in discovering and extracting the subject keywords of e-books using text mining and machine learning techniques. In this regard, three experimental approaches have been introduced and compared; including the successive implementation of the clustering process, improving the quality of clusters in terms of semantics and enriching the stop words of a specific field; Use of specialized keyword template; Finally, the use of important parts of the text in discovering and extracting key words and important topics of the text. The statistical population includes 1000 e-book titles from the subject fields of library and information science based on the congress classification system. bibliographic information of EBooks was obtained from the congress library database, then the original text was prepared. The extraction of topic keywords and clustering of training data was performed using the non-negative matrix factorization algorithm with three experimental approaches. The quality and performance of the subject clusters resulting from the implementation of three approaches in the automatic classification of experimental data were compared using a support vector machine. The findings showed that the Hamming loss (0.020) and in other words the error rate in the correct classification of experimental texts in the third approach is far less than the other two approaches. Also, the F1 score (0.82), which is the average of the two criteria of Precision (0.87) and recall (0.78) and is a reflection of the correct performance of the classification process in topic labeling of texts, is better in the third approach than the other two approaches. The results showed that the quality and semantic coherence of the subject clusters obtained from the third approach, ie the use of important parts of the text in discovering and extracting the subject, was better compared to the other two approaches. In this approach, by focusing on the main parts of the data, which represent the main content and theme of the text, more meaningful topic clusters were obtained. In addition, the keywords obtained from the topic cluster of the third approach can be used in unspecified and unknown collections in order to extract the unknown thematic content of the whole collection. The results of third approach also was better in terms of accuracy and readability (0.79) and the rate of classification error (0.020) of texts, in comparison of other two approaches.

The content analysis of the scientific papers can indicate the path of development and thematic orientations in any field. Therefore, this research aims to investigate the subjecttrends of the field of knowledge and information science in Iranian journals based on the LDA model.
The current research is descriptive and exploratory; since text-mining techniques were used to identify hidden topics and topic trends in the field of knowledge and information science based on the LDA algorithm. The statistical population of the current research includes abstracts and keywords of papers published in 11 scientific journals approved by the Iran Ministry of Science, Research, and Technology in the field of knowledge and information science during 2015-2019, which includes 1581 papers. The validity of the LDA method has been confirmed in previous studies and the reliability of the extracted data was confirmed by the inter-rater reliability method.
The findings showed that, in general, the subjects of citation analysis, library, and web were the interest subjects of researchers in the field of knowledge and information science, respectively, in the first to third place. During 2015 - 2019, the subjects of "Organizational Culture", "Social Networks", "Information Literacy", "Knowledge Management" and "Instagram" were the main subjects of the field of knowledge and information science. Another finding of the research showed that in different journals, different and sometimes common topics have been of interest to researchers in the field of knowledge and information science. Knowledge management and similar and related topics such as knowledge sharing are more important in the two journals of "The Journal of Studies in Library and Information Science" and "The Iranian Journal of Information Processing & Management". Also in most journals "Librarians" and "Users" have been among the main subjects studied.
Data mining techniques can be a suitable tool to facilitate and speed up the formulation of thematic processes in a field. In order to keep up with the journals of the field worldwide, it is necessary that the topics related to technology be considered in more journals. Also, journal editors should try to publish papers based on the policy and thematic areas overtime.

The main purpose of the present research was to investigate thematic relationships in the topics of resources used by RICeST users, using text mining techniques. Therefore, it has been attempted to reflect how the thematic relationships are in the information resources of users in the RICeST Center, in order to gain access to the required materials through understanding the behavior and feelings of users and clients.

The research method was based on text mining, which refers to data mining on the text, and text analysis in order to extract quality information from the text. Information access to the full text of articles in scientific-research, scientific-promotional journals, collections of scientific conference and conference articles, English and Persian books formed the statistical population of the research, and all the data obtained from the reporting by RICeST were checked using the census method. Data analysis and text analysis was done by Vianet software, and Python software was used to clean and normalize the data.

In order to determine the main view of the most used topics by RICeST users, based on the findings from the obtained data, 21 frequent words (used more than 2000 times in the RICeST database in a two-year interval 2018/02/08 – 2020/02/08).

the conclusion was based on the fact that the compilation of the research in the collection of electronic resources of information databases and foresight in the future of this category of resources is useful to the managers of information centers and their users.

The present study aimed to Designing a method for organizing Persian text documents using the clustering technique. The data set related to Theses and Dissertations including 2943 researches was considered as a statistical population. Data were collected from a set of data related to scientific research, which included 5,000 researches in Excel format. In this study, after converting the data into a structured format, the processing operation was performed using preprocessing operations. In the processing stage, the clustering technique was used to present the proposed algorithm in order to organize Persian text documents. This algorithm was introduced by improving the K-means algorithm for document clustering. The results of the evaluation showed that the proposed algorithm based on external criteria had a positive effect on the clustering quality of documents compared to the two algorithms K-means and K-means++. So that the research of each designated category in the related subject cluster had a uniform distribution, and led to the achievement of the purpose of the present study. In the category / cluster tables obtained from the two algorithms K-means and K-means++, we saw a non-uniform distribution of research in clusters, so the evaluation based on internal criteria was affected by different cluster densities and inter-cluster similarity. The size of the dataset was also not affected by the proposed solutions for selecting the final dataset and the research process, so the proposed algorithm works well for the high dimensions of the feature.

In our current era, with the advancements in the use of Internet, a large amount of textual data is being rapidly created. Words are an inseparable part of online transactions in E-commerce. Online comments, news, marketing and other types of communication along with the digitalization of data creates a huge amount of textual data that businesses would like to use. Textual data gets created by people, organizations and communities. In the past, researchers and businesses employed manual methods to gain insights about their customers, which required significant human effort, financial resources, and processing time. Due to human intervention in analysis, these methods were susceptible to analyst and respondent biases. By using text mining we can analyze the necessary information for companies in an automatic and cost-effective way in real time, enabling the use of the results for business model innovation. This research examines customer tweets directed at the Apple company and the company's responses using sentiment analysis methods and Latent Dirichlet Allocation. Furthermore, a new method has been suggested to combine the results of these two methods in order to gain deeper insights into the data and use the results to give recommendations for enhancing Apple company’s business model.

Identification of hot topics in research areas has always been of interest. Making smart decisions about what is needed to be studied is always a fundamental factor for researchers and can be challenging for them. The goal of this study is to identify hot topics and thematic trend analysis of articles indexed in Scopus database in the field of Knowledge and Information Science (KIS), between 2010 and 2019, by Text Mining techniques.The population consists of 50995 articles published in 249 journals indexed in Scopus database in the field of KIS from 2010 to 2019. To identify thematic clusters, algorithms of Latent Dirichlet Allocation (LDA) technique were used and the data were analyzed using libraries in Python software. To do this, by implementing the word weighting algorithm, using the TF-IDF method, and weighting all of the words and forming a text matrix, the topics in the documents and the coefficients for assigning each document to each topic (Theta) were determined. The output of the LDA algorithm led to the identification of the optimal number of 260 topics. Each topic was labeled based on the words with the highest weight assigned to each topic and with considering of experts’ opinions. Then, Topic clustering, keywords and topics identification were done. By performing calculations with 95% confidence, 63 topics were selected from 260 main topics. By calculating the average theta in years, 24 topics with a positive trend or slope (hot topic) and 39 topics with a negative trend or negative slope (cold topic) were determined. According to the results, measurement studies, e-management/ e-marketing, content retrieval, data analysis and e-skills, are considered as hot topics and training, archive, knowledge management, organization and librarians' health, were identified as cold topics in the field of KIS, in the period 2010 to 2019. The analysis of the findings shows that due to the interest of the most researchers in the last 10 years in using of emerging technologies, technology-based topics have attracted them more. In contrast, basic issues are less considered to be developed.

nowadays, a huge amount of available information on the web is text documents and articles. Text mining is a way to extract unstructured and semi-structured information from this available information on the Internet and Also, mining process of the text of knowledge and unknown, incomprehensible and potential patterns among the multitude of datasets. This research is a type of library studies. Although text mining methods are mostly based on Latin sources, but by searching Persian databases, we have found over the past decade, the subject of text mining has become doubly important for Iranian researchers, especially students of computer science and information technology; So that a significant part of the conference papers related to computer science and technology are articles related to this field. Research findings show that text mining is an application of data mining and the main difference between them is : the extraction of patterns from text with natural language in text mining, while data mining operates on structured databases. Text mining processes have two main phases: document preprocessing and knowledge extraction. So far, eight techniques have been introduced for text mining which are: Information extraction, information retrieval, text summarization, classification, clustering, visualization, natural language processing and belief mining. In recent years, much attention has been paid to text mining in the international and national spheres. The dramatic increase in textual data has prompted researchers to look for ways to explore this data. Naturally, Iranian researchers have been no exception. Text mining, with all its methods and techniques, is an effort to assist researchers in extracting useful and valuable knowledge and information from the mass of unstructured texts scattered throughout the Internet.

Probabilistic topic modeling methods consist of a set of algorithms whose main purpose is to discover the hidden subject structure in a large volume of documents. The purpose of this study is to thematically model the articles of Iranian researchers in the field of endocrinology and metabolism in the citation database of Web of Science.

The present research is of applied type and has been done by text mining and content analysis method. In this study, all required data were retrieved from the Web of Science Citation Database using the keywords registered in the medical subject heading without a time limit until November 6, 2018. Then, using a hidden allocation algorithm, the whole set of documents in MATLAB was analyzed.  

Subject categories were extracted as groups of 20 words in 10 subject categories. Then, by endocrinologists, the subject categories were named based on their relationship to various topics in the field of  endocrinology and metabolism, and each category was assigned a subject title.

The results indicate that the implementation of the latent Dirichlet allocation model has an acceptable performance in presenting the categories of endocrinology and metabolism. The extracted subject categories have good homogeneity and thematic relevance with each  other.

Topic modeling is one of the text mining techniques that allows you to discover unknown topics in a collection of documents, interpret documents based on these topics, and use these interpretations to organize, summarize, and search for texts automatically. Familiarity with the concept and technique of topic modeling, and its application in discovering topics and organizing information is one of the main goals of this research.

The present study is a review-analytical type in which, while introducing topic modeling, it has categorized and reviewed the applications of this technique based on its performance and provided a sample of research that has used this technique.

Topic modeling algorithms is used not only in addition to the three main objectives of discovering hidden topics, interpreting documents based on topics, and finally organizing and classifying texts, but also is used in discovering hidden topics and relationships in the fields of science, information retrieval, categorizing documents based on topics, discovering outstanding patterns and emerging events, clustering the concepts of scientific fields, analyzing the course of conceptual evolution during historical periods, determining the hierarchical relationships of concepts. A specific scientific field or field and vocabulary enrichment.

Topic modeling based on machine learning and artificial intelligence knowledge has been proposed as one of the new approaches to organizing information resources and serious studies are being conducted in this field. Therefore, by using topic modeling algorithms in order to automate the extraction of the subject and discover the hidden issues in the source, it is possible to strengthen and update the new systems of organizing information resources.

The current research aims to study  the terms in the literature of project management in span of time based on a word-analysis method.

The research applies word-analysis technique to automatically explore and describe the terms used in PM literature. An amount of 2170 journal were extracted from the International Journal of Project Management (IJPM). IJPM has the highest SJR index among the journals in the field of project management. The research analyze the papers of IJPM published during 1983-2016.

Ten top groups could be determined based on frequently used terms in PM. The prominent combined terms with the words management and organization are risk management, program management,   portfolio management, project organization, organizational learning, and organizational culture. The emerging terms of 2015 and 2016 are social network analysis, aerospace projects, transportation infrastructure    projects and social risk management. Four time phases in PM literature term development can be identified. Receiving new terms has been   decreasing in PM field since 2004. The term "organization" is the most frequently used term in the PM literature. Its use has increased in the span of time so its frequency percentage has increased from 21.3% in 1983-1995 to 30.7% in 1996-2005 and has finally amounted 35.1% in 2006-2016.

Conclustion: 

PM has experienced some maturity, but some scientific principles and theoretical foundations for the content are missing. Scientometric methods make it possible to identify recently emerged terms, less used terms and saturated terms. This enables us to determine the  topics of future research projects and thus to close the current gaps.

Four text mining methods are examined and focused on understanding and identifying their properties and limitations in subject discovery.

The study is an analytical review of the literature of text mining and topic modeling. 

LSA could be used to classify specific and unique topics in documents that address only a single topic. The other three text mining methods focus on topics and general partiality of the text. PLSA is applicable to documents dealing with a topic, unlike the LSA, it is used to discover general themes and contexts. However, LDA is more applicable to documents that address several issues. The CTM, method can be used to identify relationship between different subject categories.

Text mining tactics are suitable for employing analysis in discovering and extracting the text subjects.

Word co-occurrence analysis is one of the text-mining methods that has various applications in the information management area. One of these applications, which has been less noticeable, is exploring the shared semantic territory between different theoretical views. The importance of this application is due to the formation of recent scientific trends of various research areas based on different theories and concepts. Accordingly, the current study attempts to reveal the applicability of word co-occurrence analysis in exploring the shared semantic territory between two theoretical views. To this end, the dynamic capabilities and ambidexterity views were chosen as the case of this study. Dynamic capabilities and ambidexterity have had a notable co-occurrence in recent strategic management studies to the extent that researchers considered them as two integrable views. Accordingly, this study aims at exploring the structure of shared semantic territory between dynamic capabilities and ambidexterity. To this end, all scientific documents related to both theories, indexed in the Web of Science or Scopus databases, and dated to 2018 were retrieved. Then, the authors analysed the corpus composed of titles, abstracts, and keywords of collected documents by using the word co-occurrence analysis. By doing so, they introduced 14 main conceptual categories in the shared territory of these two views: 1) dynamic capabilities and their components, 2) ambidexterity and its components, 3) performance, 4) innovation, 5) organizational capabilities and resources, 6) sustainable competitive advantage, 7) organizational knowledge and learning, 8) environmental and organizational change, 9) technology and information technology, 10) leadership, 11) entrepreneurship, 12) collaboration networks, 13) business model, and 14) operations and supply chain. Also, according to the word temporal analysis, research trends among the conceptual categories were revealed. Based on these trends, it is expected that further studies in the shared semantic territory between dynamic capabilities and ambidexterity will probably tend to subjects in the fields of business model, operations and supply chain, or entrepreneurship.

The compatibility of classification codes and indexing terms done from a codified thesaurus with words and phrases that are automatically extracted using machine indexing. In designing an outo-indexing system, the computer completely replaces humans. The purpose of this research was to identify and extracting keywords and the subject trends of articles in the field of information retrieval and the subject's specificity of the author of each article by using the text mining and categorizing (classifying) with the help of concurrence vocabularies.The method of this research is applied and based on the CRISP model of data mining and text mining algorithms are used. The research community has 313 articles has in the field of information retrieval indexed at Noormags database. After normalizing the text of with the Virastyar software, during the text mining of the articles with the 7.1 version of the RapidMiner software, the keywords are extracted by their weight and the data are categorized using two classical classification algorithms, namely, KNN and Naïve Bayse were analyzed. In this study, the computer automatically indexed the readable machine text by using the frequency of the words with the help of the text mining tools of RapidMiner software. For this purpose, we use N-gram operators and calculate the weight of the words according to tf-idf method, Terms and key concepts and subject and specialization of author of each article is extracted in the form of 16 categories. Finally, the superiority of the KNN model In the categorization of the core subjects of the papers, this study is proving to be 85% more accurate than the Naïve bayse model. Finding the results of calculating the accuracy of the models indicate the acceptable performance of the RapidMiner software in machine indexing of texts. Indexing texts using this method can help improve the results of information retrieval and prevent false dropping of information in databases.

With the proliferation of the Internet and the rapid growth of electronic articles, text categorization has become one of the key and important tools for data organization and management. In the text categorization, a set of basic knowledge is provided to the system by learning from this set, the new input documents into one of the subject groups. In health literatures due to the wide variety of topics, preparing such a set of early education is a very time consuming and costly task. The purpose of this article is to present a hybrid model of learning (supervised and unsupervised) for the subject classification of health scientific products that performs the classification operation without the need for an initial labeled set. To extract the thematic model of health science texts from 2009 to 2019 at PubMed database, data mining and text mining were performed using machine learning. Based on Latent Dirichlet Allocation model, the data were analyzed and then the Support Vector Machine was used to classify the texts. In the findings of this study, model was introduced in three main steps. In the first step, the necessary preprocessing was done on the dataset due to the elimination of unnecessary and unnecessary words from the dataset and increasing the accuracy of the proposed model. In the second step, the themes in the texts were extracted using the Latent Dirichlet Allocation method, and as a basic training set in step 3, the data were backed up by the Support Vector Machine algorithm and the classifier learning was performed with the help of these topics. Finally, with the help of the categorization, the subject of each document was identified. The results showed that the proposed model can build a better classification by combining unsupervised clustering properties and prior knowledge of the samples. Clustering on labeled samples with a specific similarity criterion merges related texts with prior knowledge, then the learning algorithm teaches classification by supervisory method. Combining categorization and clustering can increase the accuracy of categorization of health texts.

: Using a co-word analysis, this study aims to mapping the intellectual structure of Iran KIS (Knowledge and Information Science) in Islamic World Science Citation Database (ISC) during two 5-year periods from 2006 to 2015. This is an applied scientometric research which uses co-word analysis. The research population consists of 2467 articles which have been published in the KIS journals and indexed in the ISC. SPSS, BibExcel and UCInet are utilized for preparing and analyzing data and also for visualizing maps. Findings showed that in the first time period (2006-2010), 7 clusters and in the second time period (2011-2016), 13 clusters were formed which in both time periods, “scientometric cluster” is the most important one. Despite the relative overlap between clusters of the two periods, the topics in the second period were of a higher number and breadth. In both periods of study, “university” is the most frequent keyword with 82 and 149 occurrences, respectively. “Journals” is the next frequent keyword in the first period, and “academic libraries” in the second period, with the occurrences of 54 and 108, respectively. The more emphasis on the IT related issues, such as digital libraries, in the second period is one of the main differences between the two time periods.

Improvement in information retrieval performance relates to the method of knowledge extraction from large amounts of text information on web. Text classification is one of application of knowledge extraction with supervised machine learning methods. This paper proposed Kullback-Leibler divergence KNN for classifying extracted features based on term weighting with Latent Dirichlet Allocation Algorithm. LDA is Non Negative matrix factorization method proposed for topic modelling and dimension reduction of high dimensional feature space .In traditional LDA, each component value is assigned using the information retrieval TF measure, While this weighting method seems very appropriate for IR, it is not clear that it is the best choice for TC problems. Actually, this weighting method does not leverage the information implicitly contained in the categorization task to represent documents. In this paper, we introduce a new weighting method based on Point wise Mutual Information for accessing the importance of a word for a specific latent concept, then each document classified based on probability distribution over the latent topics. Experimental result investigated when we used PMI measure for term Weighing and  KNN with Kullback-Leibler  distance, accuracy has been 82.5%, with lower complexity and same accuracy versus complex deep learning methods.

The classification of research studies is important in order to identify and analyze the research supply and demand in various fields of science. In particular, the classification of environmental research is essential because of its importance in Iran and its interdisciplinary nature. This research proposes One-Class Classification (OCC) method to classify the research studies in this domain using Support Vector Machine (SVM) and consequently evaluates important parameters affecting the quality of this classification. The results show that the use of descriptive metadata has better performance than the content metadata in order to make a core data set to learn the model. Moreover, the use of the polynomial kernel and the binary weighing of words in the features vector matrix leads to better results than other states. In this paper a new weighing method has been proposed which is superior to the other methods especially in precision criterion. We call this weighing method as NG-TF, which can be used in term-document matrix to determine the indicator terms of scientific domains.

This study has been done to explore the Intellectual Structure of the Positive Psychology studies. Library Studding is the approach of present research, in theoretical literature, and application in terms of the nature, and analytical in analysis of findings, and method and finally clustering have used, those are text mining techniques to explore the Intellectual Structure and relationships the topics of positive psychology studies. The populations studied in this research are the 1086 papers that are published in positive psychology topics around the world, since 2000 to 2012, and are indexed in the Scopus database. After extraction of related terms from the titles, abstracts and keywords of articles and applying text mining techniques and words stemming, a co-word matrix was created with dimensions of 43 × 43. For the interpretation of relationship major and minor categories, this matrix was standard and based on the similarity was interred to XL.STAT Software. The terms were optimized in 7 clusters. For the next steps of analysis has been used from MATHLAB software, and for display coword network from Pajak software. The results of this research show that Cluster 2 by 10, and Cluster 4 by 9 terms, are known as the principal clusters. The Cluster 5 has the most of selective terms from the major categories and Cluster 2 & 1 have minimum distance that it shows the relationship between the major and minor topics in these clusters is higher.