Narrow Results

The emergence of online social networks has revolutionized millions of web users’ behavior so that their interactions with each other produce huge amounts of data on different activities. Community detection, herein, is one of the most important tasks. The very recent trend is to detect meaningful communities based on users’ interactions or the activity network. However, in many of such studies, authors consider the basic network model while almost ignoring the model of the interactions in the multi-layer network. In this research, an experimental study is done to compare community detection in Facebook friendship network to that of activity network, considering different activities in Facebook OSN such as sharing. Then, a new community detection evaluation metric based on homophily is proposed. Eventually, a new method of community detection based on different activities in Facebook social network is presented. In this method, we generalized three familiar similarity methods, Jaccard, Common Neighbors and Adamic-Adar for multi-layered network model.

In this paper, we present a model to classify users of Social Networks. In particular, we focus on Social Network Sites. The model is based on the PageRank algorithm. We use the personalization vector to bias the PageRank to some users. We give an explicit expression of the personalization vector that allows the introduction of some typical features of the users of SNSs. We describe the model as a seven-step process. We illustrate the applicability of the model with two examples. One example is based on real links of a Facebook network. We also indicate how to take into account real actions of Facebook users to implement the model.

We study Facebook networks at 40 American universities, with focus on the comparison of their degree distributions and mechanism governing their evolution. We find that the heterogeneity indexes of these networks are all small compared with scale-free networks, and different from real-world social networks 5 Facebook networks show significant degree disassortativity; the exponent γ for the power-law model of the degree distributions is large for the networks, indicating obvious homogeneity of network structure. We calculate the goodness-of-fit between the data and power law and find that the p-values are larger than threshold 0.1 for 20 networks, implying that power law is a plausible hypothesis; we compare the power-law model with 4 alternative competing distributions and find that power-law model gives the best fit for all 40 networks. However in wider interval of degrees some other distributions, such as log-normal or stretched exponential, can give the best fit. Further based on the homogeneity of Facebook we propose an analyzable model that integrates the introduction of new vertices and edges. The edges can be established either between new vertices and old vertices or between old vertices. The model captures the real evolution processes of Facebook networks and can well reproduce their degree distributions.

In the past, enterprises used time-consuming questionnaire surveys and statistical analysis to formulate consumer profiles. However, explosive growth in social media had produced enormous quantities of texts, images, and videos, which is sometimes referred to as a digital footprint. This provides an alternative channel for enterprises seeking to gain an objective understanding of their target consumers. Facilitating the analysis of data used in the formulation of a marketing strategy based on digital footprints from online social media is crucial for enterprises seeking to enhance their competitive advantage in today’s markets. This study develops an approach for predicting consumer decision-making styles by analyzing digital footprints on Facebook to assist enterprises in rapidly and correctly mastering the consumption profile of consumers, thereby reducing marketing costs and promoting customer satisfaction. This objective can be achieved by performing the following tasks: (i) designing a process for predicting consumer decision-making styles based on the analysis of digital footprints on Facebook, (ii) developing techniques related to consumer decision-making style prediction, and (iii) implementing and evaluating a consumer decision-making style prediction mechanism. In the practical experiment, we obtained questionnaires and various digital footprint contents (including “Likes,” “Status,” and “Photo/Video”) from 3304 participants in 2018, 2644 of which were randomly selected as a training dataset, with the remaining 660 participants forming a testing dataset. The experimental results indicated that the accuracy increased to 75.88% and proved that the approach proposed in this study can effectively predict consumers’ decision-making styles.

Due to the expansion of Internet and Web 2.0 phenomenon, there is a growing interest in sentiment analysis of freely opinionated text. In this paper, we propose a novel cross-source cross-domain sentiment classification, in which cross-domain-labeled Web sources (Amazon and Tripadvisor) are used to train supervised learning models (including two deep learning algorithms) that are tested on typically nonlabeled social media reviews (Facebook and Twitter). We explored a three-step methodology, in which distinct balanced training, text preprocessing and machine learning methods were tested, using two languages: English and Italian. The best results were achieved using undersampling training and a Convolutional Neural Network. Interesting cross-source classification performances were achieved, in particular when using Amazon and Tripadvisor reviews to train a model that is tested on Facebook data for both English and Italian.

Previous studies have found that how to win an election is always an important question for legislators. Their behavior in lawmaking and constituency service is also associated with their aspirations for re-election. In the era of booming social media, how legislators can use social media to increase their chances for election and re-election has become a compelling issue. This study argues that legislators do indeed maximize the benefits of social media to win elections. On this account, this study intends to explore two main questions: (1) What kind of messages legislators choose to convey to voters on their fan pages; and (2) Whether the political characteristics of legislators affect the types of the messages they convey there. In this study, posts were collected from the fan pages of 25 Taiwanese legislators. These text messages were then converted into numerical data that could be quantitatively analyzed with the content analysis method. It was found that legislators tend to start with soft messages in their communications with the public. They share some details of their daily schedules and everyday lives with their voters before they begin image building and posting political material. This study also found that the political characteristics of legislators, including their party membership, their status either as a district or proportional representation (PR) legislator, and their incumbency all affect the content of posts on their fan pages. For example, compared to Kuomintang (KMT) and Democratic Progressive Party (DPP) legislators who share information from their daily lives, New Power Party (NPP) legislators prefer to share only political information. PR legislators devote more attention than district legislators to criticizing the government on their fan pages. Incumbents are significantly less likely than challengers to share daily information, but more likely to share political information. This study found that the aforementioned differences have resulted from the many ways that different types of legislators use to increase their chances of winning an election.

This study analyzes the transformation of marketing strategies from traditional to ’digital’ and find s out the efficacy of ’Facebook’ marketing for small or micro-enterprise brands; in the case of the restaurant industry. The study looks for the answers to questions such as How ’Facebook’ has changed the means of marketing in the case of small restaurant brands. Two restaurant brands were considered for the study. A qualitative case approach was adopted for the study. Major findings of the study have revealed that Facebook marketing is the direct, easiest and economical mode of communication with current and potential customers through ’Facebook page’, to disseminate information regarding brand and services through ’Facebook posts’, ’Comments’ and ’Chats’; besides, to maintain rapid feedback service to customers’ queries. In addition, through ’Facebook’ activities i.e., an instance of ’Likes’, ’Reviews’, ’Check-ins’, and ’Share’, customers themselves ensue as a source for promoting the brands. Nevertheless, for these small or microbrands’ Facebook Marketing, per se, it is an inexpensive technique for effective marketing; additionally, it fosters mutual relationships and increases the level of customer engagement.

This study examines how a firm’s usage of social media and banking relationships influence its value. Using a sample of 6,636 year-firm observations from 2008 to 2015, the results show that social media (Facebook, Google+, and LinkedIn) positively influence firm value, whereas bank relationships affect firm value differently: the high number of banks a firm borrows from reducing value, whereas the high bank debt a firm using creates value. The impacts of YouTube and Twitter on firm value are insignificant. Although social media have a similar function as banks in mitigating the information asymmetry between firms and outsiders, the information types vary. Banks create more soft and private information, while social media deliver more public and hard information. The accuracy of information is more than the quantity; hence, whether more information sharing via social media creates value is uncertain. We also find the substitution and complementary effects between various types of social media and banking relationships on firm value. Our results remain robust after conducting a difference-in-differences (DID) analysis using the exogenous shock of the Facebook IPO in 2012.

In order to more fully understand the cultural shifts in technology within and between generations, a sample survey of several public libraries in a rural university community will be analyzed. The following subjects will be addressed and compared on a generational level within this poster presentation: programming, technology—types and usage, and frequency and purpose of visits. A thorough analysis of the data in this case study will provide insight into the changing role of technology use among two distinct generations of library patrons.

The present study developed a prototype of blended-learning unit for enhancing students' understanding of gene expression. Then an intervention was determined the effectiveness in enhancing understanding and the perception toward an intervention in 11 juniors from a western Thai university. In this study, students had learned gene expression using Facebook group (on-line) together with face-to-face session including (1) on-line preparing, (2) active participation in class, (3) on-line content elaboration, and (4) presentation in class. We found an intervention could support students' in learning the gene expression as they gained better understanding and could explained those concepts. Equally important, students had highly positive perception toward an intervention. Moreover results showed that Facebook helped bridging the gap between teacher and students.