Examining the Growth of Online Entrepreneurship Effects on Family Income in Jordan during the Corona Virus

According to the significant impacts of social media and the internet on all facets of our lives in general and the business world in particular, many business owners and entrepreneurs who are looking to expand their clientele or start their own ventures have moved to the virtual world, particularly when they want to advance their careers. For the reasons mentioned above, this article aims to ascertain how social media networks impact business operations, with a focus on how they affect entrepreneurship growth. Facebook and Instagram are the two most useful social media platforms. The findings indicate that Facebook and Instagram have a significant impact on increasing entrepreneurship and household income in Jordan. © 2023 IEEE.

Brand Image during WAR

Due to the latest war, that unfortunately has a worldwide impact not only on humanitarian emergency, on the attacked country, but as well as at the economic level with greater international influence. Almost all countries, with very few exceptions, have interdependent economies and rely mainly on raw materials, goods, financial services, finite products, technology, know-how that are supplied by other states. We live in a Global World, where friendship, stewardship, understanding, mutual respect and the protection of humans' life must prevail both for very few "blessed", but also for all the inhabitants of the Earth. The recovery after the CoVid-19 pandemic is not complete, as the actual pandemic was not totally wiped out;many countries still need time to restore their Gross National Income, as a result, different economic sectors were likewise affected by medical emergency and restrictions. Innumerable multinational companies decided, owing to the latest war against Ukraine, to cease, suspend and even withdraw their activities, production and even brands from the aggressive country. In this article, we want to discover if appealing to this kind of measures has increased their brand image among actual and potential customers. The findings are quite intriguing.

iCompass at WANLP 2022 Shared Task: ARBERT and MARBERT for Multilabel Propaganda Classification of Arabic Tweets

Propaganda content has seen massive spread in the biggest social media networks. Major global events such as Covid-19, presidential elections, and wars have all been infested with various propaganda techniques. In participation in the WANLP 2022 Shared Task(Alam et al., 2022), this paper provides a detailed overview of our machine learning system for propaganda techniques classification and its achieved results. The task was carried out using pre-trained transformer based models: ARBERT and MARBERT. The models were fine-tuned for the downstream task in hand: multilabel classification of Arabic tweets. According to the results, MARBERT and ARBERT attained 0.562 and 0.567 micro F1-score on the development set of subtask 1. The submitted model was MARBERT which attained a 0.597 micro F1-score and got the fifth rank. © 2022 Association for Computational Linguistics.

Disparity-aware Pandemic Response Classification by Fine-Tuning Transfer Learning Approach

Interpersonal communications are being continuously passed over social media networks, and millions of users are interacting and sharing information with each other. In the COVID-19 pandemic crisis, social media platforms ignited with heated discussions between believers, deniers, and hesitating people because of the uncertainty and sometimes dis- and mis-information about the pandemic. Healthcare professional and public health authorities are also utilizing social media platforms to update the public about COVID-19 and vaccinations' impact on the personal health. However, they struggle to control the vast amount of hoaxes and rumors about the pandemic. While regardless the information source, people share and interact in different ways. Some users postulate that the information is a granted truth while some others do a fact-check. In either cases, people will have partial or full influence on others' believe. In this research, we scrutinize the effects of transfer learning across different social media platforms. We utilize different classifiers on the datasets separately and collectively to learn more about users' sentiments and reactions to healthcare statements made by authorities at specific times. Our findings show that transfer learning has little impact on how well classifiers function. © 2022 IEEE.

Resorting to Context-Aware Background Knowledge for Unveiling Semantically Related Social Media Posts

Social media networks have become a prime source for sharing news, opinions, and research accomplishments in various domains, and hundreds of millions of posts are announced daily. Given this wealth of information in social media, finding related announcements has become a relevant task, particularly in trending news (e.g., COVID-19 or lung cancer). To facilitate the search of connected posts, social networks enable users to annotate their posts, e.g., with hashtags in tweets. Albeit effective, an annotation-based search is limited because results will only include the posts that share the same annotations. This paper focuses on retrieving context-related posts based on a specific topic, and presents PINYON, a knowledge-driven framework, that retrieves associated posts effectively. PINYON implements a two-fold pipeline. First, it encodes, in a graph, a CORPUS of posts and an input post;posts are annotated with entities for existing knowledge graphs and connected based on the similarity of their entities. In a decoding phase, the encoded graph is used to discover communities of related posts. We cast this problem into the Vertex Coloring Problem, where communities of similar posts include the posts annotated with entities colored with the same colors. Built on results reported in the graph theory, PINYON implements the decoding phase guided by a heuristic-based method that determines relatedness among posts based on contextual knowledge, and efficiently groups the most similar posts in the same communities. PINYON is empirically evaluated on various datasets and compared with state-of-the-art implementations of the decoding phase. The quality of the generated communities is also analyzed based on multiple metrics. The observed outcomes indicate that PINYON accurately identifies semantically related posts in different contexts. Moreover, the reported results put in perspective the impact of known properties about the optimality of existing heuristics for vertex graph coloring and their implications on PINYON scalability.

A Systematic Approach for Contextualizing Focal Structure Analysis in Social Networks

Focal Structures are key sets of individuals who may be responsible for coordinating events, protests, or leading citizen engagement efforts on social media networks. Discovering focal structures that can promote online social campaigns is important but complex. Unlike influential individuals, focal structures can effect large-scale complex social processes. In our prior work, we applied a greedy algorithm and bi-level decomposition optimization solution to identify focal structures in social media networks. However, the outcomes lacked a contextual representation of the focal structures that affected interpretability. In this research, we present a novel Contextual Focal Structure Analysis (CFSA) model to enhance the discovery and the interpretability of the focal structures to provide the context in terms of the content shared by individuals in the focal structures through their communication network. The CFSA model utilizes multiplex networks, where the first layer is the users-users network based on mentions, replies, friends, and followers, and the second layer is the hashtag co-occurrence network. The two layers have interconnections based on the user hashtag relations. The model's performance was evaluated on real-world datasets from Twitter related to domestic extremist groups spreading information about COVID-19 and the Black Lives Matter (BLM) social movement during the 2020–2021 time. The model identified Contextual Focal Structure (CFS) sets revealing the context regarding individuals’ interests. We then evaluated the model's efficacy by measuring the influence of the CFS sets in the network using various network structural measures such as the modularity method, network stability, and average clustering coefficient values. The ranking Correlation Coefficient (RCC) was used to conduct a comparative evaluation with real-world scenarios. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Personality Traits Prediction from Text via Machine Learning

Social media platforms have been expanding their user bases. For example, LinkedIn counts 917 million monthly visitors, while Twitter has 3.62 billion monthly visitors. YouTube has 22.77 billion monthly visitors, and Instagram has 2.86 billion monthly visitors. Reports confirm data size increase of the social media networks above by 20-30% every day. With the spread of COVID-19, the same platforms have been broadly used by the worldwide collectiveness to socialize and stay amongst people. Analyzing text from Social Networking sites helps recognize individuals' personality traits automatically. A person's personality refers to their unique characteristics that shape their habits, behaviour, attitude, and cognitive tendencies. In this work, several machine learning techniques are surveyed to estimate personality traits from input text using the Myers-Briggs Type Indicator (MBTI) model. Experiments are run over a freely accessible dataset from Kaggle. In addition, techniques such as tokenization, word stemming, stop word elimination, and feature selection, utilizing TF-IDF, are used to analyze personality traits further. © 2022 IEEE.

Roles of online social media platforms and artificial intelligence in diffusing the impact of COVID-19 as scientists find a cure

Nations worldwide are currently fighting the pandemic of coronavirus disease 2019 (COVID-19) and are facing challenges in disseminating accurate and credible information to the public. During such conditions, people are seeking help from social media and social networking platforms, owing to their speed and reach, for the latest updates on the pandemic. Such alarming situations test the potential of social media and their role in providing assistance to the healthcare community. Current chapter broadly discusses the wide range of contributions made by social media platforms in acting as an information disseminating tool, a tracking tool, and also providing psychological aid to the public to elevate the positive attitude during pandemic. Spread of fake news and misinformation is a drawback faced by these platforms and they are continuously updating their technology to identify and solve this glitch. This chapter throws a brief light on how social media influencers are propitious in conveying information to the society. The chapter aims at encouraging the proper and validated use of social media and social networks in conditions of pandemic like COVID-19. © 2022 Elsevier Inc. All rights reserved.

Soft hypergraph for modeling global interactions via social media networks

Soft set theory is a map of a set of parameters to the subsets of a universe which can be utilized to parametrically model the uncertainty. On the other hand, Graph (hypergraph) theory is used to simplify some practical problems. Inspired by these concepts, the notion of “soft hypergraph” is developed as the generalization of both soft graph and hypergraph for important application in social media networking. Based on the structure of soft hypergraph, various techniques and operations are provided including soft sub-hypergraph, extended union, extended intersection, cartesian product and complement with elucidatory examples. As per the current global spread of COVID, most of the national and international interactions and social affairs have been virtually conducted via social media networks, such as Skype, Microsoft Teams, WhatsApp, Telegram, Zoom, Instagram, WeChat, etc. For the purpose of Intelligent management of network systems, we use the “generalized soft hypergraph” to model the global e-communication networking of individuals in online platforms. © 2022 Elsevier Ltd

A topic modeling method for analysis of short-text data in social media networks

Currently, many short texts are published online, especially on social media platforms. High impact events, for example, are highly commented on by users. Understanding the subjects and patterns hidden in online discussions is a very important task for contexts such as elections, natural disasters or major sporting events. However, many works of this nature use techniques that, despite showing satisfactory results, are not the most suitable when it comes to the short texts on social media and may suffer a loss in their results. Therefore, this paper presents a text mining method for messages published on social media, with a data pre-processing step and topic modeling for short texts. For this paper, we created a data set from real world tweets related to COVID-19 that is openly available1 for research purposes. © 2022, EasyChair. All rights reserved.

The Proliferation of Twitter Accounts in a Higher Education Institution

Social media networks in higher education have become effective tools. Students, instructors, staff, and society rely on social media to support educational activities, spreading information and news, and responding to user inquiries. Twitter, in particular, is considered one of the most influential social media tools in the education process. This has resulted in the emergence of many Twitter accounts affiliated with the same higher education institution. The purpose of this study was to identify the magnitude of this phenomenon and user attitudes toward it. The study was carried out at Imam Abdulrahman Bin Faisal University and included a digital exploration of all accounts that were released during the past decade and an online survey in which a sample of followers (1,200) and a group of account managers (116) participated. The results showed that multiple accounts did represent the higher education institution. Additionally,the study revealed that the COVID-19 pandemic increased the emergence of new accounts and the abandoning of existing accounts. Furthermore, users confirmed their confidence in these accounts for information and support;however, they believe that the proliferation of Twitter accounts is distracting and overwhelming. Finally, this paper reveals some recommendations and opportunities for future studies related to the subject. © 2022. All Rights Reserved.

Deep Ensemble Approach for COVID-19 Fake News Detection from Social Media

Social media networks such as Facebook and Twitter are overwhelmed with COVID-19-related posts during the outbreak. People have also posted several fake news among the massive COVID-19-related social media posts. Fake news has the potential to create public fear, weaken government credibility, and pose a serious threat to social order. This paper provides a deep ensemble-based method for detecting COVID-19 fake news. An ensemble classifier is made up of three different classifiers: Support Vector Machine, Dense Neural Network, and Convolutional Neural Network. The extensive experiments with the proposed ensemble model and eight different conventional machine learning classifiers are carried out using the character and word n-gram TF-IDF features. The results of the experiments show that character n-gram features outperform word n-gram features. The proposed deep ensemble classifier performed better, with a weighted Fl -score of 0.97 in contrast to numerous conventional machine learning classifiers and deep learning classifiers. © 2021 IEEE

Learning through social distancing: Whatsapp as a community of inquiry

Once upon a time, researchers believed that the effective use of an online social media network to support a virtual community is dependent on the participants’ interest in the context within which the community exists and the willingness of the participants to be part of mobile instant messaging groups. But I thought that interacting via WhatsApp groups will enable them to accept differing views and opinions as part of the group activities. This could ensure effective group engagement and co-creation of learning. I taught a 45 to 60 minute lesson every week to first-year students. The group was divided into smaller sub-groups and assigned individual and group tasks. I analysed the messages that they sent in the form of answers, responses and feedbacks. Four questions aligned to the community of inquiry framework, form part of this study: (1) Social presence-How has WhatsApp contributed to student’s learning? (2) Teaching presence-Has the selected mode of engagement attracted students? (3) Cognitive presence-What kind of messages were conveyed? (4) Academic performance-Has it been beneficial towards their learning and in achieving learning outcomes? Data were collected during weekly lectures to first-year students using WhatsApp as a mobile instant messaging (MIM) platform and were analysed through WhatsAnalyzer. Finally, a matrix was proposed for the analysis of various aspects of communities of practice. I discovered that WhatsApp facilitated high levels of interactivity within the groups during the COVID19 lockdown, which will change the future of remote or online teaching. However, more research needs to be carried out to understand the reasons why some students learn better than others. © the authors, 2021. All Rights Reserved.

Towards predicting COVID-19 trends: Feature engineering on social media responses

During the course of this pandemic, the use of social media and virtual networks have been at an all-time high. Individuals have used social media to express their thoughts on matters related to the pandemic. It is difficult to predict current trends based on historic case data because trends are more connected to social activities which can lead to the spread of coronavirus. So, it's important for us to derive meaningful information from social media as it is widely used. Therefore, we grouped tweets by common keywords, found correlations between keywords and daily COVID-19 statistics and built predictive modeling. The features correlation analysis was very effective, so trends were predicted very well. A RMSE score of 0.0425504, MAE of 0.03295105 and RSQ of 0.5237014 in relation to daily cases. In addition, we found a RMSE score of0.07346836, MAE of 0.0491152 and RSQ 0.374529 in relation to daily deaths. © 2021 Information Systems for Crisis Response and Management, ISCRAM. All rights reserved.