scholarly journals I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13971-13972
Author(s):  
Yang Qi ◽  
Farseev Aleksandr ◽  
Filchenkov Andrey
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Model Performance ◽  
User Profiling ◽  
Personalized Recommendation ◽  
Modal Data ◽  
Social Media Networks ◽  
The Impact

Nowadays, social networks play a crucial role in human everyday life and no longer purely associated with spare time spending. In fact, instant communication with friends and colleagues has become an essential component of our daily interaction giving a raise of multiple new social network types emergence. By participating in such networks, individuals generate a multitude of data points that describe their activities from different perspectives and, for example, can be further used for applications such as personalized recommendation or user profiling. However, the impact of the different social media networks on machine learning model performance has not been studied comprehensively yet. Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study. Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks. Our initial experimental results reveal that social network choice impacts the performance and the proper selection of data source is crucial.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

A Study Regarding Human Perception of a Company through Social Media

2019 ◽  
Vol 34 ◽  
pp. 309-314
Author(s):  
Mirona Ana Maria Popescu ◽  
Olivia Doina Negoiță ◽  
Anca Purcărea ◽  
Markus Helfert
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Human Perception ◽  
Social Media Networks ◽  
Online Social Media ◽  
The Social ◽  
Key Indicators ◽  
Different Characteristics ◽  
A Company

Of the utmost importance is finding the social networks that best fit to an industry, a company, its products / services, and last but not least, with the target audience. Each social network has different characteristics and, in addition, a different philosophy.The authors aim to carry out a bibliographic research in this paper to highlight the extent to which social networks are used. As a result, a top of social networks will be built to help raise awareness, promote products, and consolidate a strong customer-company relationship. The authors will also realize a statistical analysis of online social media networks to determine their key indicators, traffic on each platform, time spent by a user on that platform, and other key indicators, through an online tool. The results of this paper consist in presenting two classifications: the first from the perspective of the companies and the second from the perspective of social network users.

scholarly journals COMPANY IMAGE IN SOCIAL NETWORK AS PREDICTOR OF INTENTION TO APPLY FOR A JOB POSITION

2019 ◽  
pp. 209-222
Author(s):  
Neringa Vilkaite-Vaitone ◽  
Ugne Lukaite
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Labour Market ◽  
Positive Impact ◽  
Research Problem ◽  
Job Seekers ◽  
Scientific Discussion ◽  
The Impact ◽  
Job Position

This paper summarizes the arguments and counterarguments within the scientific discussion on the issue of employer attractiveness on social networks, organizational image impact upon intentions to apply for a job position in banking industry. The main purpose of the research is to theoretically and empirically evaluate the impact of attractive workplace communications on social networks and image of a bank as an employer upon intentions to apply for a job position. Systematization of literary sources and approaches for solving the research problem indicates that there exist sufficient scientific background to expect a positive impact of workplace attractiveness on the image of employer. Usage of social media is also supposed to have a positive impact on the image, while the image might be a predictor of intentions to apply for a job. The relevance of the decision of this scientific problem is that social media has a huge potential to strengthen employer’s image, however, it also might destroy a carefully formed employer’s image. Such a potential stresses the role of banks’ communications on social network for building efficient employer image. A questionnaire research of students is carried out in Lithuania. The paper presents the results of an empirical analysis, which showed that job seekers in a labour market behave similarly to consumers in a marketplace. Banks should put efforts in order to present themselves as attractive working places on social networks in order to form a favourable employer’s image and encourage job seekers to apply for positions. Results of this study indicate that usage of social networks for the formation of image of employer can be a helpful tool. This is important because there are clear links between workplace attractiveness, usage of social networks and image of an employer. The latter construct is positively related to intentions to apply for a job. The results of the research can be useful for commercial banks. This study provides banks with useful insights of the factors that determine their image in labour market. Such insights give banks a perceptible information of how to become more attractive in labour market with the help of communications on social networks.

scholarly journals Development of Novel Classifying System to Identify the Right Sense of Audio Conversation in Social Networks using Deep Convolution Neural Network

2019 ◽  
Vol 8 (2S6) ◽  
pp. 522-525
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Learning Strategies ◽  
Human Interaction ◽  
Training Data ◽  
Deep Convolutional Neural Networks ◽  
Use Of Social Media ◽  
The Right ◽  
The Impact

Social media has paved a new way for communication and interacting with others. The use of social media differs according to the socio-cultural, demographic and psychological aspects of individuals. People chat, share ideas and visual material, and feel that they satisfy their needs of belonging along with the groups they have joined. Social networks is not only a area of freedom where persons express themselves openly or furtively, but also an area where several ways of violence emerge or even a means used for some aspects of violence.. The present research throws light on a few of the regular and trendy methods of abuse and risks faced by the users of social media. Develop a system to identify abusing audio file by an individual on a people/ group based on common language, race, sexual preferences, religion, or nationality. We examine a new model from machine learning, namely deep machine learning by probing design configurations of deep Convolutional Neural Networks (CNN) and the impact of different hyper-parameter settings in identifying the negative aspects in social media. Deep CNN automatically generate powerful features by hierarchical learning strategies from massive amounts of training data with a minimum of human interaction or expert process knowledge. An application of the proposed method demonstrates excellent results with low false alarm rates for Twitter data

scholarly journals A Framework for Detecting Intentions of Criminal Acts in Social Media: A Case Study on Twitter

Information ◽  
2020 ◽  
Vol 11 (3) ◽  
pp. 154 ◽  
Author(s):  
Ricardo Resende de Mendonça ◽  
Daniel Felix de Brito ◽  
Ferrucio de Franco Rosa ◽  
Júlio Cesar dos Reis ◽  
Rodrigo Bonacin
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Online Social Networks ◽  
Communication Planning ◽  
Flexible Model ◽  
Selection Of

Criminals use online social networks for various activities by including communication, planning, and execution of criminal acts. They often employ ciphered posts using slang expressions, which are restricted to specific groups. Although literature shows advances in analysis of posts in natural language messages, such as hate discourses, threats, and more notably in the sentiment analysis; research enabling intention analysis of posts using slang expressions is still underexplored. We propose a framework and construct software prototypes for the selection of social network posts with criminal slang expressions and automatic classification of these posts according to illocutionary classes. The developed framework explores computational ontologies and machine learning (ML) techniques. Our defined Ontology of Criminal Expressions represents crime concepts in a formal and flexible model, and associates them with criminal slang expressions. This ontology is used for selecting suspicious posts and decipher them. In our solution, the criminal intention in written posts is automatically classified relying on learned models from existing posts. This work carries out a case study to evaluate the framework with 8,835,290 tweets. The obtained results show its viability by demonstrating the benefits in deciphering posts and the effectiveness of detecting user’s intention in written criminal posts based on ML.

scholarly journals Efficiency Analysis of Russian Regional Authorities on Social Networks

2021 ◽  
Author(s):  
Natalya Zimova ◽  
Egor Fomin ◽  
Aleksandra Smagina
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Effective Means ◽  
Public Confidence ◽  
Behavioral Models ◽  
Active Population ◽  
Regional Authorities ◽  
The Impact ◽  
Politically Active

Nowadays it is hardly possible to overestimate the role of digital technologies in the work of Russian politicians. One of the effective means that gives new opportunities for modern politicians is social media. The phenomenon of social media has no longer been just entertainment, it has become a powerful tool of influencing public opinion. If used properly social media can help both shape the image of a politician and increase the electorate trust and loyalty. Social networks appear to be the most accessible and popular type of social media for politicians. This article covers the topic of maintaining social network profiles by the heads of several Russian regions, moreover, the authors assess the impact on perception of politicians by the politically active population. To achieve this goal we conducted an analysis of the politician activity on the popular Russian social network VKontakte over a certain period using a special technical tool — a social media multi-factor monitoring and analyzing system developed by Russian company “Kribrum”. It contains various analysis methods, as well as linguo-semantic and psychological behavioral models. It was found that maintaining accounts on social networks contributes to the increase of public confidence in the authorities. However, the potential of this tool is not exploited to the full scale: in some cases, the heads of regions do not pay sufficient attention to maintaining their own pages on the Internet. They cannot cope with technical tools or ignore them, do not work with citizens through social networks, which eventually leads to the lack of credibility. In the modern conditions, with the federal government recognizing the importance of social media and taking into account transparency and public acknowledgement of regional authorities, the tendency towards intensifying work with citizens on virtual networks is likely to increase. Keywords: digitalization, social networks, credibility of authorities, key performance indicators (KPI)

scholarly journals The Role of Social Networks in Emergency Management

2019 ◽  
Vol 10 (4) ◽  
pp. 1346
Author(s):  
Alexey SMIRNOV ◽  
Natalia BELOZEROVA ◽  
Natalia ALANICHEVA ◽  
Irina TRUBNIKOVA ◽  
Yuriy MOTORYGIN
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Emergency Management ◽  
Information Dissemination ◽  
The Social ◽  
The Russian Federation ◽  
Definition Of ◽  
The Impact

The article is focused on the impact of social networks which are becoming increasingly important for information dissemination, user-centered response and efficient coordination between residents and governmental departments at all stages of a disaster. We intend to examine the definition of ‘social network», the most important types of emergency domain-related social media, their functions and benefits. We also propose to investigate the recent activities of the Ministry of Emergencies of the Russian Federation in the sphere of emergency prevention and risk reduction via accessing the social networks pages and assessing their effectiveness.

Board structure and corporate disclosure via social media: an empirical study in the UK

2018 ◽  
Vol 42 (5) ◽  
pp. 595-614 ◽  
Author(s):  
Mohamed A.K. Basuony ◽  
Ehab K.A. Mohamed ◽  
Khaled Samaha
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Stock Exchange ◽  
Binary Logistic Regression ◽  
Board Structure ◽  
Corporate Disclosure ◽  
Board Diversity ◽  
Content Type ◽  
The Impact

PurposeThe purpose of this paper is to investigate the impact of board structure on voluntary corporate disclosure via social media among the top 150 companies listed on the London Stock Exchange.Design/methodology/approachA disclosure index comprising of a set of items that encompass two facets of disclosure, namely corporate disclosure via social networks and social media sites, is developed and used. Binary logistic regression is used to test the research hypotheses.FindingsThe results of this study reveal the underlying relations between board composition and control variables as the determining factors of corporate disclosure, i.e. board size, board activism, board independence and board diversity (gender and ethnicity). The gender of the board can affect the corporate disclosure via a social network. The results of this study indicate that an increase in the number of female in the board members leads to higher corporate disclosure using social network. Moreover, firm size has a positive effect on corporate disclosure indicating that large firms tend to disclose more information on their websites and social networks.Practical implicationsThe paper provides new insights into the role played by the non-executive female directors in monitoring and controlling managerial processes related to corporate disclosure using social media.Originality/valueTo the best of the authors’ knowledge, this is the first paper that examines the role of board structure in monitoring and controlling management decisions and managerial processes in the area of corporate disclosure via social media.

scholarly journals Branding in the age of social media: how entrepreneurs use social networks to boost their service-based businesses

2017 ◽  
Vol 2 (1) ◽  
pp. 79-85 ◽  
Author(s):  
Alexandra Ioanid ◽  
Dana Corina Deselnicu ◽  
Gheorghe Militaru
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Business Development ◽  
Brand Name ◽  
Network Marketing ◽  
Online Activities ◽  
The Impact ◽  
A Company

Abstract The basics of product and service branding are generally the same. However, creating a brand for a company that offers services requires more effort because the services are hard to visualize and each client has different expectations. More than promoting any of the services, branding aims to create a perception of trust so that the brand name to be associated with integrity, quality, and innovation. The purpose of this paper is to determine how entrepreneurs develop their service-based business through social networks branding and also what are the benefits obtained from each method. The authors have researched previously what is the impact of social network marketing on business development and noticed that service-based businesses tend to obtain benefits from different activities comparing to product-based businesses. The authors researched through a semistructured questionnaire the online activities of 71 SMEs from Bucharest that offer various types of services to their customers. The results obtained are then correlated with the online and offline performance of the company.

Sign in / Sign up

Export Citation Format

Share Document