Home location profiling for users in social media

In this paper, we focus on the problem of estimating the home locations of users in the Twitter network. We propose a Social Tie Factor Graph (STFG) model to estimate a Twitter user's city-level location based on the user's following network, user-centric data, and tie strength. In STFG, relationships between users and locations are modeled as nodes, while attributes and correlations are modeled as factors. An efficient algorithm is proposed to learn model parameters and predict unknown relationships. We evaluate our proposed method by investigating Twitter networks. The experimental results demonstrate that our proposed method significantly outperforms several state-of-the-art methods.     

Advanced social media sentiment analysis for short-term cryptocurrency price prediction

In recent years, the scrutiny of bitcoin and other cryptocurrencies as legal and regulated components of financial systems has been increasing. Bitcoin is currently one of the largest cryptocurrencies in terms of capital market share. Therefore, this study proposes that sentiment analysis can be used as a computational tool to predict the prices of bitcoin and other cryptocurrencies for different time intervals. A key characteristic of the cryptocurrency market is that the fluctuation of currency prices depends on people's perceptions and opinions, not institutional money regulation. Therefore, analysing the relationship between social media and web search is crucial for cryptocurrency price prediction. This study uses Twitter and Google Trends to forecast the short-term prices of the primary cryptocurrencies, as these social media platforms are used to influence purchasing decisions. The study adopts and interpolates a unique multimodel approach to analyse the impact of social media on cryptocurrency prices. Our results prove that people's psychological and behavioural attitudes have a significant impact on the highly speculative cryptocurrency prices.     

Tweeting to Feel Connected: A Model for Social Connectedness in Online Social Networks

Social connectedness is an indicator of the extent to which people can realize various network benefits and is therefore a source of social capital. Using the case of Twitter, a theoretical model of social connectedness based on the functional and structural characteristics of people's communication behavior within an online social network is developed and tested. The study investigates how social presence, social awareness, and social connectedness influence each other, and when and for whom the effects of social presence and social awareness are most strongly related to positive outcomes in social connectedness. Specifically, the study looks at the concurrent direct and moderating effect of two structural constructs characterizing people's online social network: network size and frequency of usage. The research model is tested using data (n?=?121) collected from two sources: (a) an online survey of Twitter users and (b) their usage data collected directly from Twitter. Results indicate that social awareness, social presence, and usage frequency have a direct effect on social connectedness, whereas network size has a moderating effect. Social presence is found to partially mediate the relationship between social awareness and social connectedness. The findings of the analysis are used to outline design implications for online social networks from a human–computer interaction perspective.     

Understanding the online information‐seeking behaviours of young people: the role of networks of support

Information seeking is one of the most popular online activities for young people and can provide an additional information channel, which may enhance learning. In this study, we propose and test a model that adds to the existing literature by examining the ways in which parents, schools, and friends (what we call networks of support) effect young people's online information behaviours, while at the same time taking into account young people's individual characteristics, confidence, and skills to use the Internet. Using path analysis, we demonstrate the significance of networks of support in understanding the uptake of online information seeking both directly and indirectly (through enhancing self‐concept for learning and online skills). Young people who have better networks of support, particularly friends who are engaged in technology, are more likely to engage in online information seeking. While quantitative models of this nature cannot capture the complexity of individual online search practices, these findings may assist in the development of policy and practice to support young people to make the most effective use of the Internet for information seeking.     

Different worlds? A comparison of young people's home and school ICT use

Abstract This paper explores young people's access to and use of computers in the home and at school. Drawing on a questionnaire survey, conducted in 2001 and 2003 with over 1800 children in the South‐West of England, on group interviews in school with over 190 children and with visits to 11 families, the paper discusses: (1) children's current use of computers in the home and in school; 2) changing patterns of computer use in home and school between 2001 and 2003; (3) the impact of age, gender and socio‐economic area on young people's computer use in home and school. The paper then goes on to discuss young people's perceptions of the differences between home and school use of computers and to address the question of whether young people's home and school use of information and communications technologies (ICTs) are really ‘different worlds’. Through analysis of both quantitative and qualitative data, the paper proposes that the boundaries between home and school are less distinct in terms of young people's ICT use than has previously been proposed, in particular through young people's production of virtual social networks through the use of instant messenger that seem to mirror young people's social school contexts. The paper concludes by suggesting that effective home–school link strategies might be adopted through the exploration of the permeability of home/school boundaries.     

Digital Inclusion in Rural Areas: A Qualitative Exploration of Challenges Faced by People From Isolated Communities

This study explored the interplay between contextual and individual factors related to Internet adoption in isolated rural communities. By investigating 10 remote villages throughout Chile that received Internet access infrastructure in 2010–2011, we identified 3 areas in which contextual and individual factors are intertwined. First, the geographical isolation shaped people's personality and attitudes towards new experiences, including digital technologies. Second, the communities' aging population also represented a strong challenge because they lack young people, a relevant technology socialization agent. Finally, jobs and economic activities are related to people's (lack of) motivations and needs towards digital technologies. When the Internet has reached the vast majority of the population, isolated communities confront specific challenges that we need to consider in policy‐making decisions.     

The role of aesthetic,cultural, utilitarian and branding factors in young Chinese consumers' repurchase intention of smartphone brands

Despite the exponential growth of smartphone consumption, to date, very few studies have investigated the factors that influence consumers' repurchase intention of smartphone brands. China has become the world's largest consumer markets for smartphones, therefore understanding young Chinese consumers' repurchase intention in the smartphone market is of crucial importance to smartphone companies. A preliminary qualitative study based on 30 face-to-face interviews has led to the development of a new conceptual framework including aesthetic (design appeal), functional (perceived quality), brand value (brand popularity), social (subjective norm) and cultural influences (mianzi). The newly developed framework has been tested through partial least squares structural equation modeling with a sample of 321 young Chinese smartphone users. The results show that young Chinese customer's smartphone repurchase intention is mainly determined by mianzi, perceived quality, brand popularity, and design appeal. Furthermore, findings also highlight that subjective norm, perceived quality and design appeal affect Chinese people's mianzi.     

基于“互联网+”的学生顶岗实习管理系统设计

为了提高高等职业院校学生的专业实践能力,各高校十分重视学生的实践能力培养。在“互联网+”的推动下,构建基于“互联网+”的学生顶岗实习管理系统,能加强对整个顶岗实习工作过程进行科学管理,对学生的顶岗实习各项数据的收集、统计与分析等工作将更加规范、科学,更好地保障学生顶岗实习的效果和质量。     

Excessive use of Twitter among college students in the UK: Validation of the Microblog Excessive Use Scale and relationship to social interaction and loneliness

Microblogging on sites like Twitter is a growing and popular trend among young people. Apparently, some users of these microblogs exhibit addiction-like symptoms. Until recently, there was no psychometric scale to measure the excessive use of Twitter. The development of the Microblog Excessive Use Scale (MEUS) in 2014 proved a positive step in assessing this phenomenon. In the current study, we employed the MEUS to assess excessive use of Twitter in a sample of 256 college students (53.1% female; mean age 21.4 years) in the UK. Confirmatory factor analysis (CFA), calculation of criterion-related and concurrent validity and reliability were performed to assess the scale's psychometric properties. The MEUS was found to be a valid instrument for assessing excessive use of Twitter among UK college students. In addition, we found that real life social interaction was negatively associated with excessive use of Twitter and this relationship was mediated by loneliness. We compared our results with results from a previous study in which the MEUS was developed and noted some interesting differences, which might be explained by cultural differences between samples in the two studies.     

Being a Serial Transnational Activist

Transnational activism endures as a political practice turning a mirror onto the world's powerbrokers. We analyse a variety of transnational activism best characterized as serial by virtue of an observed systematic time and border‐spanning commitment to protest communication. Following statistical disambiguation of a dataset of 2.5 million unique Twitter users, we identified a subset of exceptionally prolific communicators and interviewed 21 of them. We show that a noted prominence in networked communication of otherwise unremarkable Twitter users may be an upshot of purposive strategies intended to publicize, support or help orchestrate collective action. Accordingly, we propose the term “engagement compass” to address the relationship between activists' life‐patterns and their personal investment in protest over time.     

Scheduling using tabu search methods with intensification and diversification

After spending five years in Medical School, physician students have to complete additional study including several interships before becoming full members of their professional guild. In this paper, we deal with the annual scheduling of internships taking into account the supervision capacities of the hospitals. The problem is modeled as an assignment-type problem. Several variants of Tabu Search procedures including intensification and diversification strategies are proposed and tested to deal with this problem. The numerical results indicate that the solution quality can be improved using intensification and diversification, at the expense of increasing solution time.Scope and purposeAfter spending five years in Medical School, future physicians have to complete additional study including several internships before becoming full members of their professional guild. The number of internships to be completed, their subject area, and their length depend on the student specialization. In this paper, we analyze the problem faced by the medical school each year to specify the schedule for each student's internships. For each of his internships, a student specifies preferences about its time period and the location. The objective function is to maximize the overall satisfaction of the students. The constraints correspond to the bounds (lower and upper) on the number of students that the hospitals are ready to supervise for each type of internships and for each period of the year. The problem is formulated as an assignment-type problem. To deal with this problem, we propose several variants of local search heuristic procedures including strategies to intensify the search in specific region of the feasible domain (intensification), and others to search the whole feasible domain more extensively (diversification). These variants are tested and compared to establish the tradeoff between solution time and solution quality.     

Personalized recommender system based on friendship strength in social network services

The rapid growth of social network services has produced a considerable amount of data, called big social data. Big social data are helpful for improving personalized recommender systems because these enormous data have various characteristics. Therefore, many personalized recommender systems based on big social data have been proposed, in particular models that use people relationship information. However, most existing studies have provided recommendations on special purpose and single-domain SNS that have a set of users with similar tastes, such as MovieLens and Last.fm; nonetheless, they have considered closeness relation. In this paper, we introduce an appropriate measure to calculate the closeness between users in a social circle, namely, the friendship strength. Further, we propose a friendship strength-based personalized recommender system that recommends topics or interests users might have in order to analyze big social data, using Twitter in particular. The proposed measure provides precise recommendations in multi-domain environments that have various topics. We evaluated the proposed system using one month's Twitter data based on various evaluation metrics. Our experimental results show that our personalized recommender system outperforms the baseline systems, and friendship strength is of great importance in personalized recommendation.     

Understanding the locality effect in Twitter: measurement and analysis

Twitter is one of the most popular applications in the current Internet with more than 500 M registered users across the world. In this paper, we conduct a comprehensive analysis to understand the geographical characteristics of Twitter using cross-community mining techniques. Specifically, we study the locality level shown by the three main elements of Twitter, namely users, relationships and information flow. For this purpose, we rely on a dataset including the geolocation information of more than 17, 100 and 3.5 M users, relationships and tweets, respectively. Our main findings are: (1) most of the Twitter users perform their activity from an area of at most few hundred kms covering few cities within a unique country; (2) the location (i.e., country), and in particular factors such as language or Twitter popularity within a country, dictates the level of locality in the relationships of users and Twitter conversations originated in that country. The combination of these factors reveals the presence of four types of country locality profiles that we carefully analyze and compare in the paper.     

Identifying interesting Twitter contents using topical analysis

Social media platforms such as Twitter are becoming increasingly mainstream which provides valuable user-generated information by publishing and sharing contents. Identifying interesting and useful contents from large text-streams is a crucial issue in social media because many users struggle with information overload. Retweeting as a forwarding function plays an important role in information propagation where the retweet counts simply reflect a tweet’s popularity. However, the main reason for retweets may be limited to personal interests and satisfactions. In this paper, we use a topic identification as a proxy to understand a large number of tweets and to score the interestingness of an individual tweet based on its latent topics. Our assumption is that fascinating topics generate contents that may be of potential interest to a wide audience. We propose a novel topic model called Trend Sensitive-Latent Dirichlet Allocation (TS-LDA) that can efficiently extract latent topics from contents by modeling temporal trends on Twitter over time. The experimental results on real world data from Twitter demonstrate that our proposed method outperforms several other baseline methods.     

Who is Who on Twitter–Spammer,Fake or Compromised Account? A Tool to Reveal True Identity in Real-Time

Social networks once being an innoxious platform for sharing pictures and thoughts among a small online community of friends has now transformed into a powerful tool of information, activism, mobilization, and sometimes abuse. Detecting true identity of social network users is an essential step for building social media an efficient channel of communication. This paper targets the microblogging service, Twitter, as the social network of choice for investigation. It has been observed that dissipation of pornographic content and promotion of followers market are actively operational on Twitter. This clearly indicates loopholes in the Twitter’s spam detection techniques. Through this work, five types of spammers-sole spammers, pornographic users, followers market merchants, fake, and compromised profiles have been identified. For the detection purpose, data of around 1 Lakh Twitter users with their 20 million tweets has been collected. Users have been classified based on trust, user and content based features using machine learning techniques such as Bayes Net, Logistic Regression, J48, Random Forest, and AdaBoostM1. The experimental results show that Random Forest classifier is able to predict spammers with an accuracy of 92.1%. Based on these initial classification results, a novel system for real-time streaming of users for spam detection has been developed. We envision that such a system should provide an indication to Twitter users about the identity of users in real-time.     

A fuzzy-based approach for strategic choices in electric energy supply. The case of a Swiss power provider on the eve of electricity market opening

Risk evaluation and strategic choice has become very complex for power providers, because of the growing number of uncertain parameters involved, such as energy market prices, water inflow, and demand. The lack of information and the absence of the decision maker's perception are just some of the many elements that must be accounted for. Therefore, with an approach based on fuzzy set theory, this paper aims to propose a methodology based on strategic choices that will enable decision makers to evaluate the performance of their strategies and portfolios through the computation of an indicator of economic performance, for different time-horizons. By subsequently considering the different imprecise parameters—such as the electricity spot price, the natural gas market price, rainfall and snow, etc.—in the assessment of different strategies and the analyzation of their impacts through scenario analysis, it is concluded that the resulting profit depends not only on the perception of the market player, but also on the imprecision of the variables—the same strategy may produce two different results under a different combination of parameters—as well as on the time-horizon considered. On a simple basis, it has also been possible to compare portfolios of customers.     

社交网络用户行为挖掘研究进展与展望

随着信息技术飞速发展,社交网络逐渐占领了人们日常交往、娱乐和购物等主要平台。因此,大量围绕社交网络展开的研究也变得非常热门.现有的围绕社交网络用户行为展开的研究热点主要有：基于社交网络用户行为的用户影响力研究、基于用户行为的推荐系统研究、以及社交网络用户隐私方面的研究等。社交网络是互联网的主要组成模块之一,同时也是大数据时代的主要数据提供者之一,未来对于社交网络的研究会越来越受到学术界以及工业界的更多投入,本文对社交网络用户行为挖掘的研究现状、热点展开论述,并作出展望,提出一些目前尚缺深入研究的方向,以期对读者有所帮助。     

个性化图像美学评价的研究进展与趋势

图像美学评价方法是当前研究的热点问题。图像美学评价分为大众化和个性化两种。大众化图像美学评价主要研究大多数人对图像共同的审美感知评估,而个性化图像美学评价可以针对用户的个性化审美感知进行评估。现有的研究工作主要集中在大众化图像美学评价上,但是由于人们对图像的审美体验具有高度主观性,研究针对特定用户的个性化图像美学评价方法更加符合现实意义。目前研究人员针对个性化图像美学评价展开了相关研究,并取得了一定的研究进展。但是现有的文献中缺少对个性化图像美学评价方法的综述,本文针对个性化图像美学评价的研究进展与趋势进行概述。首先分析图像美学评价的研究现状与发展趋势;然后针对现阶段的个性化图像美学评价模型进行概述,将现有的个性化图像美学评价模型总结为基于协同过滤的模型、基于用户交互的模型和基于审美差异的模型,并分析这3类模型主要的设计思路以及优缺点;最后介绍个性化图像美学评价在精准营销、个性化推荐系统、个性化视觉增强和个性化艺术设计上的应用前景,并指出未来研究工作在主观特性分析和知识驱动建模等方面的发展方向。     

UGC网站用户画像研究

近几年,社交网络的高速发展使人们的工作、生活、学习方式发生了重大改变,人们获取知识的方式呈现明显的网络化趋势.人们通过网络获取信息的同时,也在其上留下了个人的痕迹,考虑到现实中获取个人信息成本高昂,捕捉其在网络中留下的痕迹,研究其在网络社会中的“映射”,不失为一种可行的方法.用户画像作为真实用户的虚拟代表,是建立在一系列真实数据之上的用户模型.通过对“知乎”网站的深入挖掘,构建了基于用户基本属性、社交属性、兴趣属性和能力属性四个维度的动态用户画像模型,并对“知乎”网站PM 2.5话题下1303位用户进行实证分析.     

基于Stacking融合模型的Web攻击检测方法

随着计算机技术与互联网技术的飞速发展,Web应用在人们的生产与生活中扮演着越来越重要的角色。但是在人们的日常生活与工作中带来了更多便捷的同时,却也带来了严重的安全隐患。在开发Web应用的过程中,大量不规范的新技术应用引入了很多的网站漏洞。攻击者可以利用Web应用开发过程中的漏洞发起攻击,当Web应用受到攻击时会造成严重的数据泄露和财产损失等安全问题,因此Web安全问题一直受到学术界和工业界的关注。超文本传输协议(HTTP)是一种在Web应用中广泛使用的应用层协议。随着HTTP协议的大量使用,在HTTP请求数据中包含了大量的实际入侵,针对HTTP请求数据进行Web攻击检测的研究也开始逐渐被研究人员所重视。本文提出了一种基于Stacking融合模型的Web攻击检测方法,针对每一条文本格式的HTTP请求数据,首先进行格式化处理得到既定的格式,结合使用Word2Vec方法和TextCNN模型将其转换成向量化表示形式;然后利用Stacking模型融合方法,将不同的子模型(使用配置不同尺寸过滤器的Text-CNN模型搭配不同的检测算法)进行融合搭建出Web攻击检测模型,与融合之前单独的子模型相比在准确率、召回率、F1值上都有所提升。本文所提出的Web攻击检测模型在公开数据集和真实环境数据上都取得了更加稳定的检测性能。