Popular Social Networking Research Articles

Crisis Assessment Oriented Influence Maximization in Social Networks

Influence maximization (IM) aims to find a subset of k nodes that can maximize the final active node set under an information diffusion model. With the development and popularity of social networks, the IM problem plays an essential role in various applications, such as public opinion analysis, viral marketing, and rumor early warning. However, most of the existing IM solutions have not accessed the risk of negative information from nodes in the future. In reality, a company may face economic loss when negative information breaks out of its spokesman. Therefore, a crisis assessment oriented and topic-based IM problem (TIM-CA) is proposed, which is utilized to model the IM problem by considering the crisis assessment (CA) and topics of users. To solve this problem, we propose a maximum influence arborescence model-based algorithm for TIM-CA, namely, MIA-TIM-CA. The proposed algorithm consists of crisis degree calculation, topic relevance calculation, and influence spread evaluation. More importantly, as for crisis degree calculation, it considers self-, topology-, and topic-based crisis degrees for each node. At the influence spread evaluation stage, MIA-TIM-CA proposes two functions to evaluate the node's importance and node influence spread. Extensive experiments on two real-world social networks demonstrate that our MIA-TIM-CA outperforms all comparison algorithms on influence spread, crisis score, and running time.

EDITORIAL. El dilema del Editor ante las circunstancias actuales de la comunicación científica.

Recently the scientific community has been the subject of much controversy due to some facts that have arisen. One was the withdrawal of journals by the Web of Science for not carrying out adequate peer review processes and publishing articles lacking in scientific rigor in exchange for high publication costs. In fact, it can be verified that it is common to find works that appear accepted just two or three days after the date of receipt, making it doubtful of an adequate review. Many advocate “Open Science” as the freedom to commu-nicate results without the consent of referees or the sometimes very rigorous requirements of scientific journals. Another example case was that of a researcher sanctioned by his Uni-versity for considering the excessive authorship of works published by the said individual in a very short time, which seems to be doubtful. It is common to find cases of researchers advising working groups from various countries outside their country of origin, perhaps only as statistical analysts or offering their recognized names to stimulate the citation of an in-stitution or country. It would then be appropriate to ask the question: What would be the number of publications that an author may have so that it is not suspected of gratifying or convenient authorship, for himself or for the institution to which he belongs? On the other hand, it is known that authorship of papers may be obtained in high-impact journals through payments or citations that do not correspond to the topic dealt with in the work. Indeed, we have discovered some contributions with out-of-context citations in Investigación Clínicathrough a rigorous analysis of the references. Worse still, it is the communication, carried out by any individual who is not an expert in a field, through the most popular social net-works, of concepts that deeply permeate public opinion in general, being transmitted as if they were proven facts and therein the danger, in the specific case of Medicine, damage to health. For all of the above, the Editors of scientific journals must be very vigilant and ready to discuss the advantages or inconveniences of modern initiatives, the influence of social media in disseminating information, and knowing how to interpret their impact on public health. On the other hand, Journals have to balance the role of citations and impact indexes in the projection of Science individuals, as some academic institutions in European (Spain) or Asian (China) countries are doing.

Reap what you sow? Competitive diffusion in social networks with heterogeneous opinions and relationships

Nowadays, an increasing number of people use social networks to receive up-to-date information and express their personal opinions, and popular social networks have become important platforms to conduct viral-marketing for many companies. However, due to the existences of negative opinions and hostile relationships, some spreading behaviors will receive much more undesired responses. To study this process of competitive diffusion, we consider heterogeneous opinions (positive and negative ones) and heterogeneous relationships (friendly and hostile ones), and assume the reaction of a user after receiving a message is determined by the received message type, his/her own opinion and the type of relationship between him/her and the neighbor who sends this message. We then modify the duplicate forwarding model to characterize the diffusion dynamics in competitive diffusion, and define the term positive (negative) user influence which is the mean number of positive (negative) messages received by users after a user generates a message. These user influences and the corresponding diffusion threshold can be analyzed theoretically, which are verified by simulations. We then study the impacts of different factors on user influences on some real networks, and observe that messages of some type are easier to be forwarded and received in a given network if the message spreading intensity approaches the diffusion threshold and users of this type have a larger average homophily factor. These findings can help to explain why a large number of boycotts may be attracted if a user or company publishes a post or advertisement in a social network, and we believe this analysis framework will be of use for advertisers to conduct viral-marketing.

Analysis of public emotion on flood disasters in southern China in 2020 based on social media data

The exploding popularity of social networks provides a new opportunity to study disasters and public emotion. Among the social networks, Weibo is one of the largest microblogging services in China. Taking Guangdong and Guangxi in the south of China as a case, Web Scraper was used to obtain Weibo texts related to floods in 2020. The spatial distribution of floods was analyzed using Kernel Density Estimation. Public emotion was analyzed using Natural Language Processing tools. The association between floods and public emotion was explored through correlation analysis methods. The results indicated that: (1) Weibo texts could be utilized as effective data to identify urban waterlogging risk in Guangdong and Guangxi. (2) The waterlogging was mainly distributed in the southern part of Guangdong and Guangxi, especially in the provincial capitals and coastal cities. (3) Public emotion was predominantly negative, especially during periods of heavy precipitation. (4) There was a strong correlation between public emotion and floods in spatial–temporal variation. The degree of negative public emotion was significantly influenced by the number of waterlogging points. The presented results serve as the preliminary data for future planning and designing of emergency management.

TRANSFORMATION FROM PRINT NEWSPAPER TO DIGITAL: HOW EVERYTHING HAS MOVED TO SOCIAL NETWORK

The unstoppable popularity of the Internet and social media remains an undeniable fact. Popular social networks are available in many languages, they provide a wide range of communication and blur the boundaries of where a person can find and access news. The Internet environment and social networks have become the mainstream in today's realities. The present is making adjustments to all spheres of human activity, and there is a fast transformation and modification of society's informatization. The pandemic and the war have changed the way we communicate and deliver the necessary information. Social media is usually considered to be an entertainment platform, but it is worth mentioning that social media has also become a developmental and educational platform where you can find all the necessary information and find out the necessary news. The use of social media on the Internet has changed consumers' preferences and ways of finding information, as well as the speed of waiting and finding the necessary information, which significantly affects the work of journalists and the publication of news on social media.
 Recognizing that print media and news in newspapers are losing their popularity, and given the circumstances that have occurred and are occurring in the world and in Ukraine, it is easy to realize the relevance of the transition of all news to social networks. The article analyzes the changes that are taking place on the journalistic front in terms of publishing information and news. Under the influence of globalization and digitalization, the media have to transition and modify their activities and areas of work. With the changes in society, social media have become the main source of information for people, which has led to changes in journalistic activities and changes in the wishes and habits of the audience. The article also discusses the positive aspects and challenges that journalists and readers who consume information and news from social media and the Internet space may face, as it is necessary to be more attentive and critical of the information they read. 
 In the conclusion, all the information and the main idea from the article are emphasized and summarized. The positive aspects and challenges those users of news from social media and the Internet may face are described and analyzed.

Visual Transformations of the Images of Dante Alighieri's Poem "The Divine Comedy: Hell" in European Art Practices

The purpose of the article is to reveal the specifics of transformation of visual language as the artistic reflection on Dante’s images in European art practices, in particular in graphic design. The research methodology requires a comprehensive approach and involves the use of methods of art analysis, an empirical method of gathering theoretical and historical material, a method of comparison and generalization. The research uses general scientific methods, in particular the analysis and systematization of scientific literature on the topic of investiga­tion. The historical-factual method was used to identify historical processes and factors that influenced the development of transformation of the visual language of illustration and other visual practices based on it. The scientific nov­elty is in conducting a comparative analysis of visual images based on the study of visualiza­tion of classical literature works. Interpretation of the images of this classic of world literature is given by a number of artists from Sandro Botticelli to Giovanni Tommasi Ferroni, as well as the presence of images of the “Divine Com­edy” in mass and pop cultures are considered: the popularization of Dante, the exploitation of his image in the mass market through graffiti, cartoons, visual novels, websites, profiles in so­cial networks, etc. Methods of adapting Dante’s stylistics for a modern viewer, accustomed to clip products, manifestations of distribution in the most popular social networks, have been determined. Conclusions. The research shows that the unique world of visual language in the illustration and design of book publications is transformed with the help of subjective artistic vision in order to maintain the interest of a mod­ern reader of the pre-classical heritage. As a re­sult of the research, we come to the conclusion that the popularization of the image of Dante in mass culture depends on the individual factor of the world perception of the artist as a cre­ative personality. World classical art becomes the basis for the emergence of new sources of author’s creative approaches to the visual rein­terpretation of the achievements of civilization. The process of transformation of the visual lan­guage of illustrations as components of graphic design ensures long-term support of the spread of images of the “Divine Comedy” not only in Dante Alighieri’s homeland, but also in the Euro­pean art landscape.

OBILJEŽJA KORIŠTENJA SNAPCHATA KOD ZAGREBAČKIH SREDNJOŠKOLACA

CHARACTERISTICS OF »SNAPCHAT« USE AMONG ZAGREB HIGH SCHOOL STUDENTS ABSTRACT In the last decade, social networks have become one of the most important »technological tools« in the lives of people around the world, used mainly by adolescents (especially girls). Currently, the most widely used ones are Snapchat, Instagram, TikTok and Facebook. This paper aims to explore the characteristics of Snapchat use among high school students in the City of Zagreb, mainly due to its great popularity, the amount of time spent on this social network, and possible psychosocial risks, mainly due to its great popularity, but also due to the lack of domestic literature in this field. A total of 825 students participated in the study (NB=404; NG=418; 3 students did not provide gender information), and the age range was from 14 to 20 years (Mage=16.65; SDage=1.208). The results show that over 80% of high school students use Snapchat, and the differences in frequency of use were found in terms of gender, age, i.e., grade, and type ofschool. Instagram, Snapchat and TikTok are the most popular social networks among Zagreb high school students, and the use of one of these networks is moderately related to the use of the others, so the resultsspeak offor a preferred and dominantsocial network that is used more often than others. In conclusion, no differences in the severity of Internet addiction were found in relation to the frequency of Snapchat use. The results obtained allow a better understanding of the characteristics of the use of thissocial network among high school students and are interpreted in the context of the current challenges of scientific research and the possibility of developing psychosocial interventions. Key words: Snapchat; social networks; adolescents; high school students; Internet addiction.

Методология и методика изучения структуры дискурсов, плотности взаимодействия и пересечения аудиторий цифровых платформ политических сообществ

The article presents the results of methodological understanding of the process of measuring the digital infrastructure of political communities in social media. The authors study specificity of content and behavioral (interactional) markers of the digital value impact of political actors in the online network environment. The generated empirical design includes a quantitative and qualitative content- analysis of the content of materials of political communities in popular social networks of the Runet (cognitive mapping with subsequent processing of the database in SPSS Statistics 26.0), building a digital infrastructure for the intersections of their digital audiences (author's software based on R-programming language libraries) and analysis of the social graphs of these social media groups (author's software – an application to the Bloghosting VKontakte).

Effectiveness of virtual space in the socialization process of teenagers (under martial law)

The aim of the research is to study the impact of virtual space on adolescent socialization during the war by analysing the mechanisms of value formation, attitude to war, national identity and other aspects of socialization. The research involved such methods as expert evaluation, questionnaire survey, sociometry, correlation and regression analysis, as well as factor analysis using the maximum likelihood method. The methods of mathematical statistics were used. It was found that 75% of students use social networks every day, and 25% — several times a week. Instagram is the most popular social network among students, which is used by 65% of respondents, followed by Facebook with 30%, and TikTok with 20%. In general, the results of the study showed that the use of virtual space can have both positive and negative consequences for adolescents. These effects may include increased socialization and life satisfaction, but may also include the risk of developing bad habits and involvement in crime. It is important to conduct further research to understand the mechanisms of influence of virtual worlds on adolescent behaviour and to develop strategies to minimize negative consequences. Future research may be aimed at analysing different types of virtual space and their impact on adolescent socialization.

Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities.

Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That's why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutions in spam detection, as in many application areas. For this purpose, a data set was created by collecting data on the twitter platform for spam detection. In the study, fuzzy logic-based classification approaches are suggested for spam detection. In the first stage of the proposed method, a data set with extracted attributes was obtained by applying normalization and crowdsourcing approaches to the raw data obtained from Twitter. In the next stage, as a process of the data preprocessing step, six attributes in the binary form in the data set were subjected to a rating-based transformation and combined with the other real-valued attribute to create a database to be used in spam detection. Classification process inputs were obtained by applying the fisher-score method, one of the commonly used filter-based methods, to the data set obtained in the second stage. In the last stage, the data were classified based on FL based approaches according to the obtained inputs. As FL approaches, four different Mamdani and Sugeno fuzzy inference systems based on interval type-1 and Interval Type-2 were used. Finally, in the classification phase, four different machine learning (ML) approaches including support vector machine (SVM), Bayesian point machine (BPM), logistic regression (LR) and average perceptron (Avr Prc) methods were used to test the effectiveness of these approaches in detecting spam. Experimental results were obtained by applying different FL and ML based approaches on the data set created in the study. As a result of the experiments, the Interval Type-2 Mamdani fuzzy inference system (IT2M-FIS) provided the highest performance with an accuracy of 0.955, a recall of 0.967, an F-score 0.962 and an area under the curve (AUC) of 0.971. However, it has been observed that FL-based spam models have a higher performance than ML-based spam models in terms of metrics including accuracy, recall, F-score and AUC values.

Basic Psychological Needs and Psychological Well-being: The Mediating Role of Instagram Addiction

Instagram is a popular social network platform that brings benefits to many. However, for a small minority, problematic use may be an issue of concern (i.e., Instagram addiction). This addiction appears to originate from various contexts and can also have psychosocial consequences. The present study investigated the basic psychological needs and psychological well-being and the mediating role of Instagram addiction. The sample comprised 660 participants who completed a number of psychometric scales including the: Instagram Addiction Scale (15 questions), Basic Psychological Needs Scale (21 questions), and Psychological Well-being Scale (18 questions). The results confirmed the fit of the model, and showed the direct adverse and significant effects of basic psychological needs on Instagram addiction, Instagram addiction on psychological well-being, and the positive and significant direct impact of basic needs on psychological well-being. There were also significant indirect effects of basic needs (autonomy, competence, and relatedness) in well-being via Instagram addiction. The failure to satisfy basic psychological needs appears to play an important role in the addictive use of Instagram, leading to a decrease in psychological well-being.

Quantum-PSO based unsupervised clustering of users in social networks using attributes.

Unsupervised cluster detection in social network analysis involves grouping social actors into distinct groups, each distinct from the others. Users in the clusters are semantically very similar to those in the same cluster and dissimilar to those in different clusters. Social network clustering reveals a wide range of useful information about users and has many applications in daily life. Various approaches are developed to find social network users' clusters, using only links or attributes and links. This work proposes a method for detecting social network users' clusters based solely on their attributes. In this case, users' attributes are considered categorical values. The most popular clustering algorithm used for categorical data is the K-mode algorithm. However, it may suffer from local optimum due to its random initialization of centroids. To overcome this issue, this manuscript proposes a methodology named the Quantum PSO approach based on user similarity maximization. In the proposed approach, firstly, dimensionality reduction is conducted by performing the relevant attribute set selection followed by redundant attribute removal. Secondly, the QPSO technique is used to maximize the similarity score between users to get clusters. Three different similarity measures are used separately to perform the dimensionality reduction and similarity maximization processes. Experiments are conducted on two popular social network datasets; ego-Twitter, and ego-Facebook. The results show that the proposed approach performs better clustering results in terms of three different performance metrics than K-Mode and K-Mean algorithms.

Characterizing e-Cigarette-Related Videos on TikTok: Observational Study.

As a popular social networking platform for sharing short videos, TikTok has been widely used for sharing e-cigarettes or vaping-related videos, especially among the youth. This study aims to characterize e-cigarette or vaping-related videos and their user engagement on TikTok through descriptive analysis. From TikTok, a total of 417 short videos, posted between October 4, 2018, and February 27, 2021, were collected using e-cigarette or vaping-related hashtags. Two human coders independently hand-coded the video category and the attitude toward vaping (provaping or antivaping) for each vaping-related video. The social media user engagement measures (eg, the comment count, like count, and share count) for each video category were compared within provaping and antivaping groups. The user accounts posting these videos were also characterized. Among 417 vaping-related TikTok videos, 387 (92.8%) were provaping, and 30 (7.2%) were antivaping videos. Among provaping TikTok videos, the most popular category is vaping tricks (n=107, 27.65%), followed by advertisement (n=85, 21.95%), customization (n=75, 19.38%), TikTok trend (n=70, 18.09%), others (n=44, 11.37%), and education (n=6, 1.55%). By comparison, videos showing the TikTok trend had significantly higher user engagement (like count per video) than other provaping videos. Antivaping videos included 15 (50%) videos with the TikTok trend, 10 (33.33%) videos on education, and 5 (16.67%) videos about others. Videos with education have a significantly lower number of likes than other antivaping videos. Most TikTok users posting vaping-related videos are personal accounts (119/203, 58.62%). Vaping-related TikTok videos are dominated by provaping videos focusing on vaping tricks, advertisement, customization, and TikTok trend. Videos with the TikTok trend have higher user engagement than other video categories. Our findings provide important information on vaping-related videos shared on TikTok and their user engagement levels, which might provide valuable guidance on future policy making, such as possible restrictions on provaping videos posted on TikTok, as well as how to effectively communicate with the public about the potential health risks of vaping.

What Should Churches Post on Facebook? An Exploratory Study of the Perceived Contribution of Facebook Posts to the Mission of Churches

Facebook is the most popular social networking site in the world and is used by many churches. This study seeks to discover the type of Facebook posts that most contribute to the perceived spiritual formation of church attenders as defined by typical church mission statements. A broad range of church attenders who use Facebook ( N = 161) completed an online survey focusing on their church's Facebook page. They indicated the degree to which they believe various types of their church's Facebook posts contributed to their spiritual formation, specifically, their relationship with God, their relationship with fellow believers, their personal spiritual growth, and their involvement in ministry or service. They also indicated what type of posts they would like to see more frequently from their church. An exploratory analysis found that posts that had greater cognitive content (specifically, live broadcasts, video recordings, announcements, and devotionals) were perceived to contribute more to church attenders’ spiritual formation than did posts with less cognitive content (humorous memes, photos, inspirational quotations, and external links). Confirming these results, participants also expressed a preference for their church to make more posts with high cognitive content than posts with low cognitive content. These results lead to several applications of how churches can better use Facebook to contribute to their mission.

Social media prevalence study of information about carbon dioxide capture and storage projects

This article is devoted to the relevant topic of reducing the concentration of greenhouse gases in the Earth’s atmosphere. The relevance of the article is confirmed by the fact that within the framework of the Paris Agreement, a number of countries, including the Russian Federation, have undertaken obligations to implement measures entailing the achievement of this goal. Among such activities the development and implementation of carbon dioxide capture and storage projects (hereinafter referred to as CCUS projects) are important, one of the conditions for the development of which is to achieve a certain level of public approval of such projects. The article presents an overview of Russian and foreign sources of information on both the prospects for the development of projects for the capture, storage and utilization of carbon dioxide and the problems of prevalence of information about such projects. A study of four of the most popular social networks in the Russian Federation for the presence of video content and communities on topics such as “CO2”, “Greenhouse gases”, “CO2 capture”, “CO2 Utilization”, “CO2 emission” and a number of others was conducted. It was revealed that some of the topics are not represented in social networks at all, and the rest is rarely traced. Recommendations to increase the level of public awareness about CCUS projects are given.

The Influence of Social Networking on Adolescents' Social Willingness

The development of adolescents has become a hot topic of social concern. With the continuous development and expansion of the Internet, the popularity of social networking has greatly increased. Teenagers have become the main users of online social media applications, but some negativity on the Internet is more likely to have a bad influence on immature teenagers. This research mainly discusses the relationship and mechanism of adolescents' use of social networks, network social efficacy, and network interpersonal relationships. This paper utilized methodology of face-to-face interview, and analyzed under the theoretical frame of Flow Theory. The research draw a conclusion that there were 5 negative effects of the Internet on young people: addicted to online games, addicted to online dating, internet porn addiction, addicted to online information collection, and computer addiction.

I Know Your Social Network Accounts: A Novel Attack Architecture for Device-Identity Association

Online social networks revolutionize the way people interact with each other. When various social network information aggregates over time, a rich online profile of the user is formed. Owing to the various features provided by mobile devices, a user's online social activities are tightly tied to his phone, and are conveniently, sometimes unnecessarily, available to social networks. In this article, we propose a novel attack architecture to show that attackers can infer a user's social network identities behind a mobile device through new dimensions. Specifically, we first developed a correlation between a user's device system states and the social network events, which leverage multiple mechanisms such as the learning-based memory regression model, to infer the possible accounts of the user in the social network app. Then we exploited the social network to social network correlation, via which we correlated information across different social networks, to identify the accounts of the target user. We implemented and evaluated these attacks on three popular social networks, and the results corroborate the effectiveness of our design.

Fake-news-free evidence-based communication for proper vein-lymphatic disease management.

Published scientific evidence demonstrate the current spread of healthcare misinformation in the most popular social networks and unofficial communication channels. Up to 40% of the medical websites were identified reporting inappropriate information, moreover being shared more than 450,000 times in a 5-year-time frame. The phenomenon is particularly spread in infective diseases medicine, oncology and cardiovascular medicine. The present document is the result of a scientific and educational endeavor by a worldwide group of top experts who selected and analyzed the major issues and related evidence-based facts on vein and lymphatic management. A section of this work is entirely dedicated to the patients and therefore written in layman terms, with the aim of improving public vein-lymphatic awareness. The part dedicated to the medical professionals includes a revision of the current literature, summing up the statements that are fully evidence-based in venous and lymphatic disease management, and suggesting future lines of research to fulfill the still unmet needs. The document has been written following an intense digital interaction among dedicated working groups, leading to an institutional project presentation during the Universal Expo in Dubai, in the occasion of the v-WINter 2022 meeting.

Research on the Prevalence of the Use of Life Jackets and Safety Jackets Among Amateur Kayakers in Poland

Abstract Safety is one of the main aspects related to physical activities conducted on or in the immediate vicinity of water. Many people drown every year in Poland. The use of a kayak has numerous legal aspects. In the light of Polish regulations, a kayak is a ship. Vessels used on inland waterways must comply with the technical requirements and requirements for life-saving equipment set out in specific regulations. One of them is the obligation to equip the ship with life jackets in the number corresponding to the number of passengers on the ship. With the proviso that to meet the requirement it is enough to equip the ship with life jackets, and not to use them, understood as putting a life jacket on a person staying on the ship. The study was aimed at determining the attitudes and behaviors of Polish kayakers in the field of kayak use, especially regarding safety and comfort, with particular emphasis on the life jacket as a popular means of increasing safety on the water. The study was conducted in the form of an original questionnaire placed in groups of kayakers on a popular social networking site. In total, all kayaking groups in which the survey was placed count nearly 15,000 participants. The survey was anonymous and voluntary, it did not collect data about respondents. The study involved 257 people, including 172 men (67%) and 85 women (33%). The participants of the study assess their kayaking skills as: intermediate 43.6%, advanced 38.9%, beginner 9.7%, expert 7.4%, one person declared the level of "instructor". 42% of respondents declare that they kayak several dozen days a year, 37.4% - several days a year, 15.6% - one to several days a year, 4.3% - several times a week, some people gave different answers . Most respondents (72.8%) have their own life jackets. 27.2% of respondents do not have such vests, which suggests that they rent them together with kayaks. Conclusions: There is lack of coherent and clear laws regulating the safety obligations of persons using kayaks as amateurs in Poland. Among the surveyed intermediate and advanced kayakers there is high level of awareness regarding the safety of using a kayak and measures to increase safety. Among interviewed kayakers there is significant popularity of life jackets in the absence of a legal regulation considering them as basic and sufficient safety measure when kayaking.

Movie Account Recommendation on Instagram

With the increasing popularity of social networks, many businesses have started implementing their branding or targeted advertising strategies to reach potential customers through social media platforms. It is desirable and essential to help businesses to reach mass audiences and assist users to find favorite business accounts on social media platforms. In the movie industry, movie companies often create business accounts (movie accounts) to promote their movies and capture the attention of followers on Instagram. Instagram contains rich information about movies and user feedback, while IMDb, one of the most popular online databases, contains well-organized information related to movies. The features extracted from the data collected from Instagram and IMDb can complement each other. Therefore, in this study, we propose a framework for recommending movie accounts to users on Instagram by using the data collected from Instagram and IMDb platforms. The experiment results show that our proposed framework outperforms the comparing methods in terms of precision, recall, F1-score, and Normalized Discounted Cumulative Gain (NDCG) , and mitigates the effect of cold start problems. The proposed framework can help movie companies or businesses reach potential audiences and implement effective targeted advertising strategies.