Farzaneh Ghanadi Nezhad; Farideh Osareh; Mohammad Reza Ghane
Volume 20, Issue 1 , January 2022
Abstract
This study seeks to forecast the subject trend of library and information science research until 2030 based on modeling previous research topics in this field, which has been done with a text mining and in-depth learning approach. After pre-processing and thematic classification of the studies, deep ...
Read More
This study seeks to forecast the subject trend of library and information science research until 2030 based on modeling previous research topics in this field, which has been done with a text mining and in-depth learning approach. After pre-processing and thematic classification of the studies, deep neural network algorithms were used to model previous studies and forecast future topics. The study population included 90,311 journal articles in library and information science publications indexed on the Web of Science website from 1945-2020. All research processes were implemented in the Python programming language. The findings showed that the largest number of studies in the future would be related to Internet and web studies, and the growth rate of these topics will be higher in the future. However, topics related to libraries and their work processes and other traditional disciplines such as theoretical foundations will have a lower growth rate in library and information science studies. As a result, knowledge of important future issues, while helping to plan for future research, can identify study gaps and investment opportunities in the R&D sector, thereby assisting researchers, universities, and relevant research institutes in selecting projects intelligently.https://dorl.net/dor/ 20.1001.1.20088302.2022.20.1.26.9
Mohammad Bagher Dastgheib; Sara Koleini; Farzad Rasti
Volume 18, Issue 1 , February 2020, , Pages 1-15
Abstract
Nowadays the amount of textual information on the web is grown rapidly. The huge textual data needs more accurate classification algorithms. Sentiment analysis is a branch of text classification that is used to classify user opinions in case of market decisions, product evaluations or measuring consumer ...
Read More
Nowadays the amount of textual information on the web is grown rapidly. The huge textual data needs more accurate classification algorithms. Sentiment analysis is a branch of text classification that is used to classify user opinions in case of market decisions, product evaluations or measuring consumer confidence. With the rise of the production rate of Persian text data in a commercial area, improvement of the efficiency of algorithms in Persian is a must. The structure of the Persian language such as word and sentence structures poses some challenges in this area. Deep learning algorithms are recently used in NLP and especially sentiment text classification for many dominant languages like Persian. The goal is to improve the performance of classification using deep learning issues. In this work, the authors proposed a hybrid method by a combination of structural correspondence learning (SCL) and convolutional neural network (CNN). The SCL method selects the most effective pivot features so the adaptation from one domain to similar ones cannot drop the efficiency drastically. The results showed that the proposed hybrid method that is learned from one domain can act efficiently in a similar domain. The result showed that applying a combination of SCL+CNN can improve the result of sentiment classification for two domains more than 10 percent.
