Media Big Data Research Articles

Integrated news mining technique and AI-based mechanism for corporate performance forecasting

The deterioration in a corporation's profitability not only threatens its interests and sustainable development but also causes tremendous losses to other investors. Hence, constructing an effective pre-warning model for performance forecasting is an urgent requirement. Most previous studies only analyzed monetary-based ratios, but merely considering such ratios does not depict the full perspective of a corporation's business conditions. This study thus extends monetary-based ratios to non-monetary-based ratios and aggregates them through the analytic network process (ANP) with a risk-adjusted strategy to establish performance ranks of corporations. Analyzing a corporation's business relationships can help it to react to changes in the market and improve profit margins, as it draws upon such relationship networks for the transfer of scarce resources and knowledge. We believe that no current study adopts such a method to construct a forecasting model. To fill this gap in the literature, this study implements the social network (SN) technique to examine a corporation's competitive edge from seemingly noisy big media data, which are subsequently fed into an artificial intelligence (AI)-based technique to construct the model. The introduced model, examined through real-life cases under numerous conditions, offers a promising alternative for performance forecasting.

Sparse media image restoration based on collaborative low rank representation

Visual quality for image is a important problem that limits the performance in media big data analysis. To address this problem, we proposed a novel media image restoration method based on sparse representation to produce better media data to be analyzed in subsequent tasks. Sparse representation is one of the significant technique for signal processing, which aims to present the signal as the combination of several special atoms chosen from a over-completed dictionary and shows some promising results in image restoration. However, without utilizing the correlation among patches in image, the conventional sparse-based methods process the patches individually, which may not be effective enough to obtain the satisfied recovery results. Hence, in this paper, to improve the performance, an extra coding constraint based on low rank representation is introduced. The latent structure among nonlocal similar patches are firstly explored by low rank representation. And then, we exploit the structure to form a extra regularization to constrain the coding approximation between each pair of patches, which is believed to be helpful to preserve the details in image. Our extensive experiments on various benchmark images validate the effectiveness and efficient of the proposed method.

Guest Editorial: Big Media Data: Understanding, Search, and Mining

The paper in this special section focus on big data in the media industry. Big media data is a new research area, and has been attracting a lot of research interests in both industry and academia. This editorial, as the fourth part of this special issue, introduces four papers on fine-grained image classification, object retrieval, and applications of social media.

소셜미디어 빅데이터 분석을 활용한 해양스포츠 인식변화

본 연구는 소셜미디어 빅데이터를 활용하여 해양스포츠 인지 변화 추이를 살펴보고자 한다. 이를 위하여, 네이버(naver)와 다음(daum)에서 제공하는 블로그를 분석대상으로 하였다. 자료 분석 기간은 2007년 1월 1일부터 2015년 12월 31일까지 총 9년간의 자료를 선정하였다. 자료 수집 및 분석을 위하여 소셜 메트릭스 프로그램인 텍스톰(Textom)을 통해 빈도 및 메트릭스 데이터를 추출하고, Ucinet6를 사용하여 단어들 간 연결 구조 파악 및 연결정도 중심성을 분석하고 관계의 정도를 계량화 하였다. 시각화를 위해 Ucinet6의 넷드로(NetDraw)기능을 이용하여 해양스포츠와 관련된 단어들 사이의 네트워크를 시각화하였다. 또한 유사점을 가진 단어들이 형성하는 군집을 도출하기 위해 CONCOR분석을 실시하였다. 키워드를 바탕으로 연관어를 살펴본 결과, 첫째, 2007년 해양스포츠, 관광, 리조트, 해변, 섬, 2008년 해양스포츠, 관광, 바다, 해변, 리조트, 2009년 해양스포츠, 관광, 바다, 해변, 리조트, 2010년 해양스포츠, 바다, 관광, 전국해양스포츠, 해변, 2011년 해양스포츠, 관광, 바다, 해변, 리조트, 2012년 해양스포츠, 관광, 바다, 스킨스쿠버, 보라카이, 2013년 해양스포츠, 전국해양스포츠, 관광, 바다, 하와이, 2014년 해양스포츠, 관광, 바다, 체험, 스킨스쿠버, 2015년 해양스포츠, 발리, 관광, 체험, 괌 순으로 핵심 키워드가 나타났다. 둘째, 연결 정도 중심값을 살펴보면, 2007년 해양스포츠, 관광, 리조트, 섬, 해변, 2008년 해양스포츠, 바다, 관광, 해변, 리조트, 2009년 해양스포츠, 관광, 바다, 해변, 리조트, 2010년 해양스포츠, 바다, 관광, 리조트, 해변, 2011년 해양스포츠, 관광, 바다, 해변, 리조트, 2012년 해양스포츠, 관광, 바다, 스킨스쿠버, 보라카이, 2013년 해양스포츠, 관광, 바다, 하와이, 스킨스쿠버, 2014년 해양스포츠, 관광, 바다, 스킨스쿠버, 체험, 2015년 해양스포츠, 관광, 발리, 바다, 체험 순으로 연결 정도 중심 값이 높은 것으로 나타났다. 셋째, CONCOR 분석결과 2007년 `신혼여행`, `관광1`, `관광2`, `해양스포츠`, 2008년 `신혼여행`, `관광`, `동력해양스포츠`, `무동력해양스포츠`, 2009년 `신혼여행 및 관광`, `해양스포츠`, `관광요인`, 2010년 `관광`, `신혼여행`, `관광요인`, `해양스포츠`, 2011년 `관광 및 해양스포츠`, `신혼여행`, 2012년 `해양스포츠`, `관광`, `신혼여행`, 2013년 `관광`, `전국해양스포츠제전`, `해양스포츠`, 2014년 `신혼여행 및 관광 패키지`, `관광`, 2015년 `신혼여행 및 관광 패키지`, `관광`의 그룹이 형성되었다.

Predicting Retweeting Behavior Based on BPNN in Emergency Incidents

Emergency incidents can trigger heated discussions on microblogging platforms, and a great number of tweets related to emergency incidents are retweeted by users. Consequently, social media big data related to the emergency incidents is generated from various social media platforms, which can be used to predict users’ retweeting behavior. In this paper, the characteristics of individuals’ retweeting behaviors in emergency incidents are analyzed, and then 11 important characteristics are extracted from recipient characteristics, retweeter characteristics, tweet content characteristics, and external media coverage. A back propagation neural network (BPNN) model called PRBBP is used to predict retweeting behavior in such emergency incidents. Based on PRBBP, an algorithm called PRABP is proposed to predict the number of retweets in emergency incidents. The experiments are performed on a large-scale dataset crawled from Sina weibo. The simulation results show that both the PRBBP model and the PRABP algorithm proposed by this paper have excellent predictive performance.

Guest Editorial: Big Media Data: Understanding, Search, and Mining

The paper in this special section focus on big data in the media industry. Big media data is a new research area, and has been attracting a lot of research interests in both industry and academia. This editorial, as the fourth part of this special issue, introduces four papers on fine-grained image classification, object retrieval, and applications of social media.

A comparison of sentiment analysis techniques with a social media big data set

No abstract available.

Spatial network of urban tourist flow in Xi’an based on microblog big data

ABSTRACTThe mobile internet and social media have changed people’s travel behavior. During a journey, tourists generate a large amount of ‘digital footprint’ that can be used for studying tourist behavior. Exploring tourist spatial behavior based on social media big data is a new research field. Using the example of Xi’an, this study attempts to reveal the characteristics of tourists’ spatial network of tourist flow behavior rules and the function of travel areas and nodes by analyzing the spatial network of tourist flow using social network analysis and data visualization based on microblog-geotagged big data generated by tourists. Geotagged messages are obtained from the Open API of the Sina Microblog. This study found that tourism development shows characteristic of spatial aggregation. The Bell Tower, Qujiang, and Lintong areas are the most crucial tourism development areas in Xi’an. Furthermore, there are obvious hierarchical characteristics in a tourism spatial network. Travel nodes can be divided into three levels, namely pivotal, important and ordinary nodes. Famous scenic spots and traffic hubs are the most important sites that tourists visit. Moreover, the travel route can be divided into four types: synthetic routes, urban-center routes, the Qujiang travel route, and the Lintong travel route. The findings can provide a foundation for tourism cooperation, tourism planning, accurate marketing, travel route design, and other works.

Guest Editorial: Big Media Data: Understanding, Search, and Mining (Part 2)

The articles in this special section focus on Big Data. In the first part of this special issue, we have introduced three papers on large scale similar image search, image search quality improvement, and semi-supervised multi-label image annotation. This second part of this special issue includes two examples on large scale visual retrieval. The contributions cover two themes: visual semantic relationship learning and large scale indexing.

The methodology of a multi-model project examining how facebook infrastructures social relations

ABSTRACTIt is the purpose of this paper to make explicit the methodology (the theory of the methods) by which we conducted research for an Economic and Social Research Council-funded research project on the relationship of values to value. Specifically, we wanted to study the imperative of Facebook to monetize social relationships, what happens when one of our significant forms of communication is driven by the search for profit, by the logic of capital. We therefore wanted to ‘get inside’ and understand what capital's new lines of flight, informationally driven models of economic expansion, do to social relations. Taking up the challenge to develop methods appropriate to the challenges of ‘big data', we applied four different methods to investigate the interface that is Facebook: we designed custom software tools, generated an online survey, developed data visualizations, and conducted interviews with participants to discuss their understandings of our analysis. We used Lefebvre's [(2004). Rhythmnanalysis: Space, time and everyday life. London: Continuum] rhythmanalysis and Kember and Zylinska's [(2012). Life after new media: Mediation as a vital process. Cambridge, MA: MIT Press] ideas about ‘lifeness’ to inform our methodology. This paper reports on a research process that was not entirely straightforward. We were thwarted in a variety of ways, especially by challenge to use software to study software and had to develop our project in unanticipated directions, but we also found much more than we initially imagined possible. As so few academic researchers are able to study Facebook through its own tools (as Tufekci [(2014). Big questions for social media big data: Representativeness, validity and other methodological pitfalls. In ICWSM ‘14: Proceedings of the 8th International AAAI Conference on Weblogs and Social Media (pp. 505–514)] notes how, unsurprisingly, at the 2013 ICWSM only about 5% of papers were about Facebook and nearly all of these were co-authored with Facebook data scientists), we hope that our methodology is useful for other researchers seeking to develop less conventional research on Facebook.

Guest Editorial: Big Media Data: Understanding, Search, and Mining

The papers in this special section focus on the topic of Big Data. There has been an explosive increase in media data, such as images, videos and social media in the Internet, mobile devices, and desktops. Accordingly, the area of big media data has been attracting a lot of research interest from both academia and industry. Big media data offers a promising possibility for in-depth media understanding, as well as exploring the very big scale media data to bridge the well-known semantic gap between high-level semantics and low-level features. It provides richer information, ranging from social relations to context information associated to rich media data of diverse modalities. It also provides us the opportunity to mine reliable and helpful knowledge from big media data for a wide variety of applications.

A note on software tools and technologies for delivering smart media-optimized big data applications in the cloud

Welcome tothespecial issueofSpringer Computing onSoftware Tools and Technologies for Delivering Smart Media-Optimized Applications in the Cloud. This special issue deals with the intersection of big media data and it needs for exploiting elastic cloud computing services for efficiently processing and analysing such big data to support emerging media-optimised applications.

Cognitive mechanism related to line drawings and its applications in intelligent process of visual media: a survey

Line drawings, as a concise form, can be recognized by infants and even chimpanzees. Recently, how the visual system processes line-drawings attracts more and more attention from psychology, cognitive science and computer science. The neuroscientific studies revealed that line drawings generate similar neural actions as color photographs, which give insights on how to efficiently process big media data. In this paper, we present a comprehensive survey on line drawing studies, including cognitive mechanism of visual perception, computational models in computer vision and intelligent process in diverse media applications. Major debates, challenges and solutions that have been addressed over the years are discussed. Finally some of the ensuing challenges in line drawing studies are outlined.

Towards the Development of a Framework for Socially Responsible Software by Analyzing Social Media Big Data on Cloud Through Ontological Engineering

A socially responsible internet is the need of the hour considering its huge potential and role in educating and transforming the society. Social computing is emerging as an important area as far as development of next generation web is concerned. With the proliferation of social networking applications, vast amount of data is available on cloud, which may be analyzed to gain useful insight into behavioral and linguistic patterns of different cultural and socio-economic groups further classified on the basis of gender and age etc. The idea is to come up with an appropriate framework for socially responsible software artifacts. These artifacts will monitor online social network data and analyze it from the perspective of socially responsible behavior based on ontological engineering concepts. Identification of socially responsible agents is such an example, though based on a different approach. More examples may be taken from literature dealing with microblog analytics, social semantic web, upper ontology for social web, and social-network-sourced big data analytics. In the present work, it is proposed to focus on analysis/monitoring of socially responsible behavior of social media big data and develop an upper level ontology as the framework/tool for such an analytics.