Abstract This paper presents an approach based on supervised machine learning methods to build a classifier that can identify text complexity in order to present Arabic language learners with texts suitable to their levels. The approach is based on machine learning classification methods to discriminate between the different levels of difficulty in reading and understanding a text. Several models were trained on... This paper presents an approach based on supervised machine learning methods to build a classifier that can identify text complexity in order to present Arabic language learners with texts suitable to their levels. The approach is based on machine learning classification methods to discriminate between the different levels of difficulty in reading and understanding a text. Several models were trained on a large corpus mined from online Arabic websites and manually annotated. The model uses both Count and TF-IDF representations and applies five machine learning algorithms; Multinomial Naïve Bayes, Bernoulli Naïve Bayes, Logistic Regression, Support Vector Machine and Random Forest, using unigrams and bigrams features. With the goal of extracting the text complexity, the problem is usually addressed by formulating the 'level identification' as a classification task. Experimental results showed that n-gram features could be indicative of the reading level of a text and could substantially improve performance, and showed that SVM and Multinomial Naïve Bayes are the most accurate in predicting the complexity level. Best results were achieved using TF-IDF Vectors trained by a combination of word-based unigrams and bigrams with an overall accuracy of 87.14% over four classes of complexity. Read More Read Less

Abstract Purpose: Disaster social media has become an important research topic in many disciplines, such as public management and emergency response. To understand the present and future status of disaster social media, the purpose of this paper is to systematically summarize the topic distribution, characteristics, and development trends of disaster social media research. Design/Methodology/Approach: By using Bibexcel, R and Ucinet, temporal-spatial analysis, clustering analysis, and social network analysis are performed on... Purpose: Disaster social media has become an important research topic in many disciplines, such as public management and emergency response. To understand the present and future status of disaster social media, the purpose of this paper is to systematically summarize the topic distribution, characteristics, and development trends of disaster social media research. Design/Methodology/Approach: By using Bibexcel, R and Ucinet, temporal-spatial analysis, clustering analysis, and social network analysis are performed on a bibliometric dataset of disaster social media articles obtained from the Web of Science database. And then, based on the results of the clustering and social network analyses, several major topics under the perspectives of emergency management and information dissemination were qualitative summarized in detail. Based on the results of the temporal-spatial analysis and qualitative analysis, the hot topics and future trends in disaster social media research are identified. Findings: The results indicate that the available research hot topics and methods are becoming highly diverse, and dynamics analysis, quantitative mining, and emotional calculations may become a future trend in social media research. Read More Read Less

Abstract Purpose: In the era of knowledge-driven economy, the method of transforming the potential of information resources into actual social and economic values is increasingly becoming significant. As the development of government procurement information continuously deepens, the existing construction, management, and service platform patterns cannot adapt to the development requirements. A method was proposed in this paper to solve the main problems of government procurement information development and the corresponding information... Purpose: In the era of knowledge-driven economy, the method of transforming the potential of information resources into actual social and economic values is increasingly becoming significant. As the development of government procurement information continuously deepens, the existing construction, management, and service platform patterns cannot adapt to the development requirements. A method was proposed in this paper to solve the main problems of government procurement information development and the corresponding information service process. Design/Methodology/Approach: This research establishes a collaboration-based model by analyzing and extracting the main features of the value chains in government procurement information service. Such a method was developed by combing the main constituent elements and linking rules of government procurement information chains. Moreover, value curve theory is used to expound on how government procurement intelligent cloud information service adds value to the entire information service chain. Read More Read Less