QUANTIFICATION OF LARGE TEXT ARRAYS DESTRUCTIVENESS IN SOCIAL MEDIA

Author(s):  
Владимир Александрович Минаев ◽  
Александр Валерьевич Симонов

Цель исследования состоит в разработке методики, позволяющей выявлять деструктивность больших текстовых массивов в социальных медиа. Проведен анализ существующих подходов к определению деструктивного характера текстовых данных, дано описание их преимуществ и недостатков. Описан метод определения деструктивности текста с использованием векторных представлений слов. Рассмотрено формирования векторных представлений слов и оценена возможность их применения при решении задач идентификации текстового контента. Обосновано применение алгоритмов Word2vec и FastText. Предложены ключевые слова и выражения векторных представлений слов, определяющих три класса текстов: реабилитация нацизма, радикальный ислам, антисемитизм. Реализованы модели выявления деструктивности контента больших текстовых массивов с использованием нейтральных новостных корпусов текстов и текстов, содержащих возможный деструктивный контент. Произведена интерпретация результатов анализа текстовых массивов и обоснована Word2vec как наиболее подходящая модель векторного представления слов. Сделан вывод о направлениях использования полученных результатов в аналитической деятельности государственных органов, общественных организаций и социальных медиа для выявления противоправного контента. The aim of the study is to develop a method that allows us to identify the destructiveness of large text arrays in social media. The analysis of existing approaches to determining the destructive nature of text data is carried out, and their advantages and disadvantages are described. A method for determining the destructiveness of a text using vector representations of words is described. The formation of vector representations of words is considered and the possibility of their application in solving problems of identifying text content is evaluated. The application of the Word2vec and FastText algorithms is justified. Keywords and expressions of vector representations of words defining three classes of texts are proposed: rehabilitation of Nazism, radical Islam, and anti-Semitism. Models are implemented to identify the destructiveness of the content of large text arrays using neutral news text corpora and texts containing possible destructive content. The results of the analysis of text arrays are interpreted and Word2vec is justified as the most suitable model for the vector representation of words. The conclusion is made about the directions of using the obtained results in the analytical activities of state authorities, public organizations and social media to identify illegal content.

Author(s):  
Piotr Szamrowski ◽  
Adam Pawlewicz

The main objective of this paper is to identify the platforms and social media tools utilized by the brewing industry in communication with the stakeholders, mainly with potential clients. In addition, the study sought to determine the nature of the published content, identify those responsible for their management, and present the advantages and disadvantages of their conduct in communication and creating the image of the company. The results indicate that only 25% of the surveyed companies do not use social media in PR. This applies only to small enterprises, with regional character. All the major brewing companies in their public relations activities use at least one type of social media, focusing in most cases on social networking (Facebook) and Video Sharing (YouTube). In addition, some of the largest brands included in the individual equity groups have their own social media channels used to communicate with the stakeholders. General promotion of company products and, what is very important, creating a dialogue with social media platform community, were seen as the most important benefits of using social media.


2021 ◽  
Vol 15 (3) ◽  
pp. 1-19
Author(s):  
Wei Wang ◽  
Feng Xia ◽  
Jian Wu ◽  
Zhiguo Gong ◽  
Hanghang Tong ◽  
...  

While scientific collaboration is critical for a scholar, some collaborators can be more significant than others, e.g., lifetime collaborators. It has been shown that lifetime collaborators are more influential on a scholar’s academic performance. However, little research has been done on investigating predicting such special relationships in academic networks. To this end, we propose Scholar2vec, a novel neural network embedding for representing scholar profiles. First, our approach creates scholars’ research interest vector from textual information, such as demographics, research, and influence. After bridging research interests with a collaboration network, vector representations of scholars can be gained with graph learning. Meanwhile, since scholars are occupied with various attributes, we propose to incorporate four types of scholar attributes for learning scholar vectors. Finally, the early-stage similarity sequence based on Scholar2vec is used to predict lifetime collaborators with machine learning methods. Extensive experiments on two real-world datasets show that Scholar2vec outperforms state-of-the-art methods in lifetime collaborator prediction. Our work presents a new way to measure the similarity between two scholars by vector representation, which tackles the knowledge between network embedding and academic relationship mining.


Author(s):  
Emma Ferrett ◽  
Stefan Dollinger

Abstract In this paper we discuss advantages and disadvantages of e-dictionaries over print dictionaries in order to answer one increasingly relevant question: is digital always better? We compare the e-content from Oxford University Press and Merriam-Webster flagship dictionaries against their most recent print counterparts. The resulting data shows that the move from print to digital, against popular perception, results in a loss of lexicographical detail and scope. After assessing the user-friendliness of the e-dictionaries’ sites in both desktop and mobile app formats, we conclude that Merriam-Webster currently utilizes the digital medium somewhat better, while Oxford University Press is the current market leader in collaborations with tech giants such as Google. Most crucially, however, both companies have yet to devise and implement optimal ways to balance advertising noise and lexicographical content. Finally, we compare the virtual popularity of e-dictionaries according to their social media efforts and product partnerships. The greatest problem e-dictionaries currently face is that content does routinely change in unspecified and even undocumented ways. Despite these significant disadvantages, the convenience of mobile online accessibility appears to outweigh the concern with the reliability and quality of content.


Author(s):  
Terri Schmitt ◽  
Susan Sims-Giddens ◽  
Richard Booth

As technological advances continue to expand connectivity and communication, the number of patients and nurses engaging in social media increases. Nurses play a significant role in identification, interpretation, and transmission of knowledge and information within healthcare. Social media is a platform that can assist nursing faculty in helping students to gain greater understanding of and/or skills in professional communication; health policy; patient privacy and ethics; and writing competencies. Although there are barriers to integration of social media within nursing education, there are quality resources available to assist faculty to integrate social media as a viable pedagogical method. This article discusses the background and significance of social media tools as pedagogy, and provides a brief review of literature. To assist nurse educators who may be using or considering social media tools, the article offers selected examples of sound and pedagogically functional use in course and program applications; consideration of privacy concerns and advantages and disadvantages; and tips for success.


2020 ◽  
Vol 5 (3) ◽  
pp. 309-330
Author(s):  
Rifni Rizqi Nurul Aliyati ◽  
Wiryo Setiana ◽  
Acep Aripudin

Pesan dakwah dapat disampaikan melalui media termasuk instagram. Trend  tersebut memiliki dua sisi seperti pisau bermata ganda (tantangan). Penelitian ini bertujuan untuk mengetahui penyajian pesan dakwah dalam media sosial instagram. Tujuan penelitian ini mengetahui bentuk penyajian pesan dakwah dalam instagram dan mencari tahu kelebihan dan kekurangan penyajian pesan dakwah dalam media sosial. Metode penelitian yang digunakan adalah deskriptif dengan pendekatan kualitatif dan teknik pengumpulan datanya, melalui observasi dan dokumentasi. Hasil penelitian menunjukan bahwa dari dua puluh unggahan yang diteliti, terdapat tiga unggahan yang termasuk bentuk penyajian pesan dakwah informatif, empatbelas unggahan yang termasuk persuasif, dan tiga unggahan yang termasuk koersif. Kelebihan penyajian pesan dakwah pada akun instagram ini ialah menyampaikan pesan dalam bahasa singkat dan mudah dipahami pembaca. Dan kekurangannya, yaitu penjelasan yang kurang lengkap dan singkat. Kelebihan dan kekurangannya ini juga memberikan dampak pada pemahaman  pembacanya. Da'wah messages can be conveyed through the media including Instagram. The trend has two sides like a double-edged knife (a challenge). This study aims to determine the presentation of preaching messages on social media Instagram. The purpose of this study is to find out the form of preaching messages on Instagram and find out the advantages and disadvantages of preaching messages in social media. The research method used is descriptive qualitative approach and data collection techniques, through observation and documentation. The results showed that of the twenty uploads examined, there were three uploads that included informative preaching messages, fourteen uploads that were persuasive, and three uploads which were coercive. The advantage of presenting da'wah messages on this Instagram account is that it conveys messages in short and easily understood language. And the shortcomings, namely an incomplete and concise explanation. These strengths and weaknesses also have an impact on the reader's understanding.


Author(s):  
Елена Макарова ◽  
Elena Makarova ◽  
Дмитрий Лагерев ◽  
Dmitriy Lagerev ◽  
Федор Лозбинев ◽  
...  

This paper describes text data analysis in the course of managerial decision making. The process of collecting textual data for further analysis as well as the use of visualization in human control over the correctness of data collection is considered in depth. An algorithm modification for creating an "n-gram cloud" visualization is proposed, which can help to make visualization accessible to people with visual impairments. Also, a method of visualization of n-gram vector representation models (word embedding) is proposed. On the basis of the conducted research, a part of a software package was implemented, which is responsible for creating interactive visualizations in a browser and interoperating with them.


2021 ◽  
Vol 6 (42) ◽  
pp. 74-82
Author(s):  
Mohd Fadhil Aziz ◽  
Mardzelah Makhsin

The impact of social media use on behavior among Students of Higher Education institutions nowadays needs to be given serious attention. Many teenagers are influenced by the views shared on social media and cause the emergence of negative behavior problems at home or in educational institutions. The existence of these problems among teenagers is definitely a factor or cause that needs to be identified. Therefore, this study was conducted to identify the level of frequency of social media use and its relationship with the appearance of behavior among community college students in terms of socializing, communication, dressing, and entertainment. Social media and its impact on adolescents is a very broad issue and needs to be studied in depth all the time as its development and rapidity are always happening. The research only focused on three types of social media like Facebook, Youtube, and Instagram. This study was conducted qualitatively using the library research method by making research on books and journals. The findings that have been identified show that there are many advantages and disadvantages of social media for adolescents, especially in the aspects studied. This study is very important because it can make students aware that social media can influence negative morals and help all educators at all levels improve their teaching system by emphasizing the relevant elements to avoid negative social problems among male and female students.


Vector representations for language have been shown to be useful in a number of Natural Language Processing tasks. In this paper, we aim to investigate the effectiveness of word vector representations for the problem of Sentiment Analysis. In particular, we target three sub-tasks namely sentiment words extraction, polarity of sentiment words detection, and text sentiment prediction. We investigate the effectiveness of vector representations over different text data and evaluate the quality of domain-dependent vectors. Vector representations has been used to compute various vector-based features and conduct systematically experiments to demonstrate their effectiveness. Using simple vector based features can achieve better results for text sentiment analysis of APP.


Social media is very useful in present scenario. It is powerful medium to circulate all informations in present time. The whole world becomes a village through social media. The study examines the impact of social media on society in Haryana. This study was conducted in Rohtak district of Haryana. The interview scheduled method was employed. In this study, 240 respondents were selected by purposive sampling. The objectives of the study were to find out the attitude of the people towards reliability of social media; to know the attitude of the people about advantages and disadvantages of social media. On the basis of this study researcher found that the youth belonged to different age, and education group indicate their varied responses on impact of social media on society.


Sign in / Sign up

Export Citation Format

Share Document