A framework for real-time semantic social media analysis

This paper presents a framework for collecting and analysing large volume social media content. The real-time analytics framework comprises semantic annotation, Linked Open Data, semantic search, and dynamic result aggregation components. In addition, exploratory search and sense-making are supported through information visualisation interfaces, such as co-occurrence matrices, term clouds, treemaps, and choropleths. There is also an interactive semantic search interface (Prospector), where users can save, refine, and analyse the results of semantic search queries over time. Practical use of the framework is exemplified through three case studies: a general scenario analysing tweets from UK politicians and the public’s response to them in the run up to the 2015 UK general election, an investigation of attitudes towards climate change expressed by these politicians and the public, via their engagement with environmental topics, and an analysis of public tweets leading up to the UK’s referendum on leaving the EU (Brexit) in 2016. The paper also presents a brief evaluation and discussion of some of the key text analysis components, which are specifically adapted to the domain and task, and demonstrate scalability and efficiency of our toolkit in the case studies.     

Deep sentiment analysis: Mining the causality between personality-value-attitude for analyzing business ads in social media

IT vendors routinely use social media such as YouTube not only to disseminate their IT product information, but also to acquire customer input efficiently as part of their market research strategies. Customer responses that appear in social media, however, are typically unstructured; thus, a fairly large data set is needed for meaningful analysis. Although identifying customers’ value structures and attitudes may be useful for developing targeted or niche markets, the unstructured and volume-heavy nature of customer data prohibits efficient and economical extraction of such information. Automatic extraction of customer information would be valuable in determining value structure and strength. This paper proposes an intelligent method of estimating causality between user profiles, value structures, and attitudes based on the replies and published content managed by open social network systems such as YouTube. To show the feasibility of the idea proposed in this paper, information richness and agility are used as underlying concepts to create performance measures based on media/information richness theory. The resulting deep sentiment analysis proves to be superior to legacy sentiment analysis tools for estimation of causality among the focal parameters.     

User comments for news recommendation in forum-based social media

News recommendation and user interaction are important features in many Web-based news services. The former helps users identify the most relevant news for further information. The latter enables collaborated information sharing among users with their comments following news postings. This research is intended to marry these two features together for an adaptive recommender system that utilizes reader comments to refine the recommendation of news in accordance with the evolving topic. This then turns the traditional “push-data” type of news recommendation to “discussion” moderator that can intelligently assist online forums. In addition, to alleviate the problem of recommending essentially identical articles, the relationship (duplicate, generalization, or specialization) between recommended news articles and the original posting is investigated. Our experiments indicate that our proposed solutions provide an improved news recommendation service in forum-based social media.     

Applying social learning analytics to message boards in online distance learning: A case study

Social learning analytics introduces tools and methods that help improving the learning process by providing useful information about the actors and their activity in the learning system. This study examines the relation between SNA parameters and student outcomes, between network parameters and global course performance, and it shows how visualizations of social learning analytics can help observing the visible and invisible interactions occurring in online distance education.The findings from our empirical study show that future research should further investigate whether there are conditions under which social network parameters are reliable predictors of academic performance, but also advises against relying exclusively in social network parameters for predictive purposes. The findings also show that data visualization is a useful tool for social learning analytics, and how it may provide additional information about actors and their behaviors for decision making in online distance learning.     

SAMAR: Subjectivity and sentiment analysis for Arabic social media

SAMAR is a system for subjectivity and sentiment analysis (SSA) for Arabic social media genres. Arabic is a morphologically rich language, which presents significant complexities for standard approaches to building SSA systems designed for the English language. Apart from the difficulties presented by the social media genres processing, the Arabic language inherently has a high number of variable word forms leading to data sparsity. In this context, we address the following 4 pertinent issues: how to best represent lexical information; whether standard features used for English are useful for Arabic; how to handle Arabic dialects; and, whether genre specific features have a measurable impact on performance. Our results show that using either lemma or lexeme information is helpful, as well as using the two part of speech tagsets (RTS and ERTS). However, the results show that we need individualized solutions for each genre and task, but that lemmatization and the ERTS POS tagset are present in a majority of the settings.     

Dissecting emotion and user influence in social media communities: An interaction modeling approach

Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.     

Social impacts in social media: An examination of perceived truthfulness and sharing of information

Twitter, Facebook, and other social media display the combined opinion of users as collective opinion. The purpose of the work reported here was to examine how collective opinion might influence the perceived truthfulness and the sharing likelihood of health-related statements on social media. Experiment 1 revealed that, when evaluating the truthfulness of a statement, participants adopted the collective truthfulness rating associated with the statement. Similarly, Experiment 2 showed that the likelihood that participants would share a statement followed the collective sharing likelihood associated with the statement. These social impacts were extensive, taking place for statements perceived as true, debatable, and false. These results contribute new insights into how people perceive and share information on social media as well as how collective opinion might affect the quality of information on social media.     

A motives framework of social media website use: A survey of young Americans

Social media is increasingly important in daily life and is an especially important social interaction mechanism for young people. Although research has been conducted evaluating user types based on motives for using social media, no such framework has been extended to social media websites. We extend previous research by evaluating the underlying structure of social media website usage motivations using a 13 item survey and evaluations from 19 different social media websites administered to 1686 young Americans. Using a multidimensional scaling approach, we uncover 2 major motive dimensions underlying social media website use: fun-related and content-specific. Based on the derived dimensions, we generate a graphical “quadrant” system for classifying social media websites and depict all 19 social media sites based on their quadrant. We propose that our quadrant system can be used by other researchers to further refine understanding of social media website usage motives.     

Medical social network content analysis for medical image retrieval purpose

Background and objective: Medical social networking platforms provide virtual spaces ensuring the interaction between different healthcare participants. As a part of the exchange, these spaces allow subscribers to upload medical images, describing different medical cases for an analysis or an interpretation proposal. Facing this expected huge amount of uploaded images generated daily, it is needed to engage new mechanisms to effectively deal with this circumstance, for enhancing the search function process of medical images, based on what is uploaded. To overcome this issue, setting up of images visual searching based on a content-based medical image retrieval scheme is the solution. More clearly, such mechanism will help and motivate medical social networking subscribers to find visually similar stored images. Methods: To ensure this task, the development of this mechanism, technically, is based mainly on a fusion of three visual features, which offers a flexible and more precision. It is reinforced by a weighted distance approach through attributing weights for feature vectors to scale up the performance. Indeed, the displayed results of this system can be updated based on user's intention by a user interactive feedback mechanism to indicate the truly relevant images. Results: We provide the theoretical performance of our scheme. Extensive experiments were conducted on a categorically classified collection containing 500 images. We conduct a practical evaluation on this dataset classes, putting returned results in a comparative study with other models results, existing in the literature. Conclusions: The proposed scheme preserves the efficiency of the search task. As theoretically and experimentally established, our scheme offers an effective image retrieval model that can support different subscribers' expectations. The relevance feedback mechanism can keep the dynamism of the system, thus offering a continuous searching result evolution. Experimentation outcomes indicate better findings compared with the other models.     

Branding with social media: User gratifications,usage patterns,and brand message content strategies

The emergence of social media provides a new platform for developing brand–consumer relationships. The aim of the current study is to examine the differences in Chinese users’ gratifications of different social media and the impact of brand content strategies on the quality of brand–consumer communication via social media. In the first study, 209 SNS and 161 microblog users were surveyed. Five dimensions of social media gratifications emerged from the factor analysis. Significant differences in the strengths of gratifications were found between SNS and microblog users. Usage patterns of SNS and microblog are analyzed and compared. In the second study, we examined the impact of users’ gratification and the type of social media on the effectiveness of different brand content strategies through a two-week experiment involving 60 SNS users and 61 microblog users. Implications for developing branding strategies on different social media platforms are discussed.     

An assessment of equivalence between paper and social media surveys: The role of social desirability and satisficing

Investigation of the underlying mechanisms responsible for measurement variance has received little attention. The primary objective of this study is to examine whether paper and social media surveys produce convergent results and investigate the underlying psychological mechanisms for the potential measurement nonequivalence. Particularly, we explored the role of social desirability and satisficing on the measurement results. We collected data via five different survey modes, including paper survey, ad hoc Web survey, online forum (message boards)-based, SNS-based and microblog-based surveys. The findings show that socially desirable responding does not lead to inconsistent results. Rather we found that satisficing causes inconsistent results in paper versus online surveys. Sociability reduces the possibility of engaging in satisficing that results in inconsistent results between traditional Web surveys and social media-based Web surveys.     

A bilingual approach for conducting Chinese and English social media sentiment analysis

Due to the advancement of technology and globalization, it has become much easier for people around the world to express their opinions through social media platforms. Harvesting opinions through sentiment analysis from people with different backgrounds and from different cultures via social media platforms can help modern organizations, including corporations and governments understand customers, make decisions, and develop strategies. However, multiple languages posted on many social media platforms make it difficult to perform a sentiment analysis with acceptable levels of accuracy and consistency. In this paper, we propose a bilingual approach to conducting sentiment analysis on both Chinese and English social media to obtain more objective and consistent opinions. Instead of processing English and Chinese comments separately, our approach treats review comments as a stream of text containing both Chinese and English words. That stream of text is then segmented by our segment model and trimmed by the stop word lists which include both Chinese and English words. The stem words are then processed into feature vectors and then applied with two exchangeable natural language models, SVM and N-Gram. Finally, we perform a case study, applying our proposed approach to analyzing movie reviews obtained from social media. Our experiment shows that our proposed approach has a high level of accuracy and is more effective than the existing learning-based approaches.     

Healthcare support for underserved communities using a mobile social media platform

Emerging digital technologies for healthcare information support have already contributed to reducing the digital divide among rural communities. Although mobile health (m-health) applications facilitate provision of support for treatment consultation in real-time, their substantial potential has not yet been operationalised for decision support to meet citizen demand in developing nations. Modern healthcare information access, especially in rural areas of developing countries, is critical to effective healthcare, since both information and expert opinions are limited. Mobile phone and social media penetration, however, is often extensive. In this paper, we design and evaluate an innovative mobile decision support system (MDSS) solution for rural citizens healthcare decision support and information dissemination.Developed using a design science approach, the instantiated artifact connects underserved rural patients in Bangladesh to general practitioners (GPs) – allowing GPs, based on queries and information support provided, to evaluate patient conditions virtually and provide answers for further diagnosis or treatment. A cloud platform using social media embodies health record information and is used with a rating technique that matches queries to profiled remote experts, participating asynchronously. A comprehensive evaluation of the MDSS artifact ensures its utility, efficacy, and reliability.     

DYSCS: A platform to build geographically and semantically enhanced social content sites

Social content sites allow ordinary internet users to upload, edit, share, and annotate Web content with freely chosen keywords called tags. However, tags are only useful to the extent that they are processable by users and machines, which is often not the case since users frequently provide ambiguous and idiosyncratic tags. Thereby, many social content sites are starting to allow users to enrich their tags with semantic metadata, such as the GeoSocial Content Sites, for example, where users can annotate their tags with geographic metadata. But geographic metadata alone only unveils a very specific facet of a tag, which leads to the need for more general purpose semantic metadata. This paper introduces DYSCS – Do it Yourself Social Content Sites – a platform that combines Web 2.0 and Semantic Web technologies for assisting users in creating their own social content sites enriched with geographic and general purpose semantics. Moreover, DYSCS is highly reusable and interoperable, which are consequences of its ontology driven architecture.     

Communication in the face of a school crisis: Examining the volume and content of social media mentions during active shooter incidents

Little is known about the effectiveness of social media in delivering information during active shooter incidents at the P-12 level. This study analyzed social media activity that occurred during and after two active shooter events on September 30, 2014. Over 5000 social media posts from Facebook, Twitter, blogs, and mainstream news outlets were analyzed. Social media analysis outlined the scope of online communication during the first week following the incidents, revealed social media frequency, increases in conversation, misinformation, and differences between parent and student posts. Results revealed spikes in social media chatter following the release of the identities of shooters and victims. Consistent with media dependency theory and the high levels of uncertainty characteristic of the incident, users’ social media posts contained more information than affect displays during the active shooter event. Implications for scholars and P-12 administrators are discussed.     

The influence of user interaction and participation in social media on the consumption intention of niche products

Social media may be particularly adept at promoting niche products because of the tendency of consumers to participate in generating reviews and discussing such products, thereby raising interest in them. In this study, we investigate how patterns of user interaction in discussing a niche cultural product may influence participation levels, which in turn enhance consumption intentions. We show that higher levels of participation can indeed enhance consumption intention. Furthermore, interaction patterns with high inclusiveness and betweenness centralization may enhance participation levels, whereas out-degree centralization and core-periphery have a detrimental influence. Implications for research and practice are discussed.     

VIRTUE: A visual tool for information retrieval performance evaluation and failure analysis

Objective: Information Retrieval (IR) is strongly rooted in experimentation where new and better ways to measure and interpret the behavior of a system are key to scientific advancement. This paper presents an innovative visualization environment: Visual Information Retrieval Tool for Upfront Evaluation (VIRTUE), which eases and makes more effective the experimental evaluation process.Methods: VIRTUE supports and improves performance analysis and failure analysis.Performance analysis: VIRTUE offers interactive visualizations based on well-known IR metrics allowing us to explore system performances and to easily grasp the main problems of the system.Failure analysis: VIRTUE develops visual features and interaction, allowing researchers and developers to easily spot critical regions of a ranking and grasp possible causes of a failure.Results: VIRTUE was validated through a user study involving IR experts. The study reports on (a) the scientific relevance and innovation and (b) the comprehensibility and efficacy of the visualizations.Conclusion: VIRTUE eases the interaction with experimental results, supports users in the evaluation process and reduces the user effort.Practice: VIRTUE will be used by IR analysts to analyze and understand experimental results.Implications: VIRTUE improves the state-of-the-art in the evaluation practice and integrates visualization and IR research fields in an innovative way.     

Networked narratives on Humans of New York: A content analysis of social media engagement on Facebook

Humans of New York (HONY) is a popular Facebook page which has more than 13 million fans. The posts on HONY are termed as networked narratives, which are stories told on social media with technology affordances enabling story co-construction between the story tellers and the readers. A content analysis (N = 390) was conducted to examine the popular topics on networked narratives and its impact on social media engagement as represented by the number of likes, the number of shares, and likability of characters featured in the post. Results revealed a set of topics of the networked narratives were associated with social media engagement. Also, the tone and the length of posts were associated with social media engagement.     

Connected scholars: Examining the role of social media in research practices of faculty using the UTAUT model

Social media has become mainstream in recent years, and its adoption has skyrocketed. Following this trend among the general public, scholars are also increasingly adopting these tools for their professional work. The current study seeks to learn if, why and how scholars are using social media for communication and information dissemination, as well as validate and update the results of previous scholarship in this area. The study is based on the content analysis of 51 semi-structured interviews of scholars in the Information Science and Technology field. Unlike previous studies, the current work aims not only to highlight the specific social media tools used, but also discover factors that influence intention and use of social media by scholars. To achieve this, the paper uses the Unified Theory of Acceptance and Use of Technology (UTAUT), a widely adopted technology acceptance theory. This paper contributes new knowledge to methodological discussions as it is the first known study to employ UTAUT to interpret scholarly use of social media. It also offers recommendations about how UTAUT can be expanded to better fit examinations of social media use within scholarly practices.     

Research intelligence involving information retrieval – An example of conferences and journals

This paper reports a work that was intended to reveal the connection between topics investigated by conference papers and journal papers. This work selected hundreds of papers in data mining and information retrieval from well-known databases and showed that the topics covered by conference papers in a year often leads to similar topics covered by journal papers in the subsequent year and vice versa. This study used some existing algorithms and combination of these algorithms to proposed a new detective procedure for the researchers to detect the new trend and get the academic intelligence from conferences and journals.The goal of this research is fourfold: First, the research investigates if the conference papers’ themes lead the journal papers’. Second, the research examines how the new research themes can be identified from the conference papers. Third, the research looks at a specific area such as information retrieval and data mining as an illustration. Fourth, the research studies any inconsistencies of the correlation between the conference papers and the journal papers.This study explores the connections between the academic publications. The methodologies of information retrieval and data mining can be exploited to discover the relationships between published papers among all topics. By discovering the connections between conference papers and journal papers, researchers can improve the effectiveness of their research by identifying academic intelligence.This study discusses how conference papers and journal papers are related. The topics of conference papers are identified to determine whether they represent new trend discussed in journal papers. An automatic examination procedure based on information retrieval and data mining is also proposed to minimize the time and human resources required to predict further research developments. This study develops a new procedure and collects a dataset to verify those problems. Analytical results demonstrate that the conference papers submitted to journals papers are similar each year. Conference papers certainly affect the journal papers published over three years. About 87.23% of data points from papers published in 1991–2007 support our assumption. The research is intended to help researchers identify new trend in their research fields, and focus on the urgent topics. This is particularly valuable for new researchers in their field, or those who wish to perform cross-domain studies.