Search

Community detection is an important area of research in social media mining. Numerous algorithms have been developed to detect disjoint, overlapping, and dynamic communities in a network. However, most of the existing algorithms do not consider the influence of each node in a group, which may be different and can affect the result of community detection. In this paper, we have proposed a novel Louvain-based algorithm named “NI-Louvain,” which considers the influence of each node in a group that not only detects community but also most influential nodes in the community. The proposed algorithm works in three steps. First, the input graph is processed to reduce its density. This is done by calculating cliques from the graph. In second step, Louvain's multilevel algorithm is applied to this clique graph. The resultant community obtained has a better modularity value than the communities obtained from existing algorithms like edge betweenness, label propagation, leading eigen, Louvain, fast greedy, walktrap, and infomap. In the third step, the nodes of resultant communities are transformed back to the nodes of the original graph. This step is beneficial in detecting overlapping communities, fuzzy membership of each node, most influential node in each community formed, and outlier nodes.

Location-based social media data can offer useful insights on the spatial and temporal dynamics of public attitudes. In this study, we aim to investigate the gendered attitudes toward transit services in China, utilizing the case of Shenzhen. We collected 44,257 Weibo microblogs, a major source of social media data in China, and applied a series of text mining and visualization techniques to examine the gender differences among our focused themes. The microblogs reveal a distinct gender gap in terms of quantity, as nearly 74% are posted by women. While women tend to be more concerned about the comfort of transit environment (e.g., temperature, crowdedness, and safety, especially at night), men tend to be more interested in transit systems’ e-payment services and reporting traffic incidents. Overall, this study presents a methodological framework and empirical case study about how we can utilize certain social media mining techniques to investigate gendered, subjective travel experiences, providing researchers and practitioners with an innovative way to gather customer service feedback and build more inclusive service systems.

The IT service industry values the experience of social familiarity, which is based on routine interactions with suppliers and customers and is at the frontier of social media marketing. To further understand how IT service companies use social media to engage their customers or potential leads, the objectives of this research are to delineate the differences between IT service companies’ use of social media and users’ expectations based on knowledge extracted from user-generated content on Twitter. We applied a text mining approach called two-tier concept-linking analysis to extract patterns in Twitter posts from top IT service companies as well as the related tweets from the Twitter users. We further compare the yearly similarities and differences of the key concepts from the company’s official account and from the users. Besides, the key concepts between users’ expectations and IT service companies’ social media use were compared on the basis of first-tier concepts and further elaborated by their corresponding second-tier concepts. Our approach contributes to further understand the socio-cognitive insights underlying the dynamic social media data, from which organizations and individuals in charge can note the objectives they wish to maintain and the marketing gaps they wish to improve on.

11th International Conference on City Logistics, DUBROVNIK, CROATIE, 12-/06/2019 - 14/06/2019; City Logistics is characterized by multiple stakeholders that often have different views of such a complex system. From a public policy perspective, identifying stakeholders, issues and trends is a daunting challenge, only partially addressed by traditional observation systems. Nowadays social media is one of the biggest channels of public expression and it is often used to communicate opinions and content related to City Logistics. The idea of this research is that analysing social media content could help in understanding the public perception of City logistics. This paper proposes a methodology for collecting content from Twitter and implementing Machine Learning techniques (unsupervised learning and Natural Language Processing), to perform content and sentiment analysis. The proposed methodology is applied to more than 110 000 tweets containing City Logistics key-terms. Results allowed building an Interest Map of concepts and a Sentiment Analysis to determine if City Logistics entries are positive, negative or neutral.

Signed graphs are often used as models for social media mining, social networks analysis and nature language processing. In this paper, we study clustering algorithms for signed graphs that can be scaled for use in large-scale signed networks. A proposed mechanism, called a random walk gap (RWG), is used to extract more cluster structure information. RWG uses two types of random walks on signed graphs. The first considers positive edges only. The second takes negative edges into account. Three types of edges in signed graphs are identified and their different characteristics in terms of transition probability changes are determined for the two types of random walk graphs. Different characteristics contain different information about cluster structure and a RWG matrix is used to reflect the differences. The RWG matrix is used to adjust the weights of edges in signed graphs. This is the first study to perform a random walk on negative edges. A fast clustering for signed graphs (FCSG) algorithm is then proposed. This FCSG is compared with existing methods. The computational times for different algorithms are measured. The experiments show that the proposed FCSG algorithm gives better results than existing algorithms based on the performance criteria of imbalance and modularity.

Technological development of the last several decades has driven open innovation towards organizational, business, social, and economic change. Open innovation has emerged as the main driver of change in a business sector that needs to be flexible and resilient, rapidly adapting to change through innovation. In this context, the present study aimed to explore the limits of open innovation by extracting evidence from user-generated content (UGC) on Twitter using social media mining. To this end, in terms of the methodology, we first applied machine learning Sentiment Analysis algorithm texted using Support Vector Classifier, Multinomial Naïve Bayes, Logistic Regression, and Random Forest Classifier to divide the sample of n = 586.348 tweets into three groups expressing the following three sentiments: positive, negative, and neutral. Then, we used a mathematical topic modeling algorithm known as Latent Dirichlet allocation to analyze the tweet databases. Finally, Python was used to develop textual analysis techniques under the theoretical framework of Computer-Aided Text Analysis and Natural Language Processing. The results revealed that, in the tweets dataset, there were eight topics. Of these topics, two contained tweets expressing negative sentiments (Culture and Business Models/Management), three topics contained tweets expressing positive sentiments (Communities, Creative projects and Ideas), and three topics contained tweets expressing neutral sentiments (Entrepreneurship, Teams and Technology). These topics are discussed in the context of limitations, risks, and characteristics of open innovation according to the UGC on Twitter. The paper concludes with the formulation of 20 limits of open innovation and 27 research questions for further research on open innovation, as well as a discussion of theoretical and practical implications of the study. UGCUser-Generated ContentUGDUser-Generated DataCATAComputer-Aided Text AnalysisNLPNatural Language ProcessingLDALatent Dirichlet AllocationSVCSupport Vector ClassifierMNBMultinomial Naïve BayesLRLogistic RegressionRFCRandom Forest Classifier

Social media data have recently attracted considerable attention as an emerging voice of the customer as it has rapidly become a channel for exchanging and storing customer-generated, large-scale, and unregulated voices about products. Although product planning studies using social media data have used systematic methods for product planning, their methods have limitations, such as the difficulty of identifying latent product features due to the use of only term-level analysis and insufficient consideration of opportunity potential analysis of the identified features. Therefore, an opportunity mining approach is proposed in this study to identify product opportunities based on topic modeling and sentiment analysis of social media data. For a multifunctional product, this approach can identify latent product topics discussed by product customers in social media using topic modeling, thereby quantifying the importance of each product topic. Next, the satisfaction level of each product topic is evaluated using sentiment analysis. Finally, the opportunity value and improvement direction of each product topic from a customer-centered view are identified by an opportunity algorithm based on product topics’ importance and satisfaction. We expect that our approach for product planning will contribute to the systematic identification of product opportunities from large-scale customer-generated social media data and will be used as a real-time monitoring tool for changing customer needs analysis in rapidly evolving product environments.

Background Although birth defects are the leading cause of infant mortality in the United States, methods for observing human pregnancies with birth defect outcomes are limited. Objective The primary objectives of this study were (i) to assess whether rare health-related events—in this case, birth defects—are reported on social media, (ii) to design and deploy a natural language processing (NLP) approach for collecting such sparse data from social media, and (iii) to utilize the collected data to discover a cohort of women whose pregnancies with birth defect outcomes could be observed on social media for epidemiological analysis. Methods To assess whether birth defects are mentioned on social media, we mined 432 million tweets posted by 112,647 users who were automatically identified via their public announcements of pregnancy on Twitter. To retrieve tweets that mention birth defects, we developed a rule-based, bootstrapping approach, which relies on a lexicon, lexical variants generated from the lexicon entries, regular expressions, post-processing, and manual analysis guided by distributional properties. To identify users whose pregnancies with birth defect outcomes could be observed for epidemiological analysis, inclusion criteria were (i) tweets indicating that the user’s child has a birth defect, and (ii) accessibility to the user’s tweets during pregnancy. We conducted a semi-automatic evaluation to estimate the recall of the tweet-collection approach, and performed a preliminary assessment of the prevalence of selected birth defects among the pregnancy cohort derived from Twitter. Results We manually annotated 16,822 retrieved tweets, distinguishing tweets indicating that the user’s child has a birth defect (true positives) from tweets that merely mention birth defects (false positives). Inter-annotator agreement was substantial: κ = 0.79 (Cohen’s kappa). Analyzing the timelines of the 646 users whose tweets were true positives resulted in the discovery of 195 users that met the inclusion criteria. Congenital heart defects are the most common type of birth defect reported on Twitter, consistent with findings in the general population. Based on an evaluation of 4169 tweets retrieved using alternative text mining methods, the recall of the tweet-collection approach was 0.95. Conclusions Our contributions include (i) evidence that rare health-related events are indeed reported on Twitter, (ii) a generalizable, systematic NLP approach for collecting sparse tweets, (iii) a semi-automatic method to identify undetected tweets (false negatives), and (iv) a collection of publicly available tweets by pregnant users with birth defect outcomes, which could be used for future epidemiological analysis. In future work, the annotated tweets could be used to train machine learning algorithms to automatically identify users reporting birth defect outcomes, enabling the large-scale use of social media mining as a complementary method for such epidemiological research.

Internet technology improved the way people can interconnect and exchange information among each other. Increasing usage of online social networks for collection of news and information is also the main cause of rumor i.e. substances of information which are not verified when they are posted on social media sites. This paper discusses types of rumors that spread among social networks named as long standing rumors which disseminate for a long period and newly emergent rumors procreated through a rapid activity like breaking news. Paper is given an outline of study into social network rumors for the decisive aim of creating a classification method which contains four modules: rumor detection, tracking, stance classification and rumor veracity classification. We investigate the methods offered in the scientific literature for the improvement of such elements. Paper concludes with ideas for imminent investigation in social media mining for the recognition and perseverance of rumors.

Despite the ubiquity of e-Participation initiatives, efforts in mainstreaming social media-based and citizen-led political deliberations are still limited. Consequently, there is little opportunity to leverage, study and understand the expected mutual re-shaping of deliberations on traditional e-Participation and spontaneous citizen discussions on social media platforms. This mutual re-shaping phenomenon also referred to as “duality of e-Participation”; requires inter alia a Social Software Infrastructure (SSI) to enable decision makers in government access relevant information about ongoing citizen discussions on social media platforms. This article describes the design of such SSI. The design is based on a comprehensive set of requirements specifying relevant technical capabilities required to support a number of core facets of an integrated e-Participation model. In addition, the paper describes the software components for realizing the design and how an implementation of the SSI was employed as part of an e-Participation initiative in Europe. We conclude with some of the socio-technical challenges associated with implementing of some of the components of the Social Software Infrastructure.

Web 2.0 allows people to express and share their opinions about products and services they buy/use. These opinions can be expressed in various ways: numbers, texts, emoticons, pictures, videos, audios, and so on. There has been great interest in the strategies for extracting, organising and analysing this kind of information. In a social media mining framework, in particular, the use of textual data has been explored in depth and still represents a challenge. On a rating and review website, user satisfaction can be detected both from a rating scale and from the written text. However, in common practice, there is a lack of algorithms able to combine judgments provided with both comments and scores. In this paper we propose a strategy to jointly measure the user evaluations obtained from the two systems. Text polarity is detected with a sentiment-based approach, and then combined with the associated rating score. The new rating scale has a finer granularity. Moreover, also enables the reviews to be ranked. We show the effectiveness of our proposal by analysing a set of reviews about the Uffizi Gallery in Florence (Italy) published on TripAdvisor.

The availability of social media-based data creates opportunities to obtain information about consumers, trends, companies and technologies using text mining techniques. However, the quality of the data is a significant concern for social media-based analyses. The aim of this study was to mine tweets (microblogs) to explore trends and retrieve ideas for various purposes such as product development, technology and sustainability-oriented considerations. The core methodological approach was to create a classification model to identify tweets that contained an idea. This classification model was used as a pre-processing step so the query results obtained from the application programming interface were cleared from the messages that contained the search terms used in the query but did not contain an idea. The results of this study demonstrate that our method based on text mining, and supervised or semi-supervised classification methods, can extract ideas from social media. The social media data mining process illustrated in our study can be utilised as a decision-making tool to detect innovative ideas or solutions about a product or service and summarise them into meaningful clusters. We believe that our findings are significant for the sustainability, tech mining and innovation management communities.

The cycle of traditional disaster loss assessment methods is too long because the assessment results need to be passed among multiple issues. Such a long cycle causes relevant departments to be unable to make emergency decisions in a timely manner. This paper builds a dynamic and real-time model for disaster loss assessment based on social media data. This model presents a method for mining quantitative human loss information from social media data and a truth discovery algorithm for handling social media data conflicts. An experiment using the actual data of the Jiuzhaigou earthquake is conducted to verify the model. The results confirm that the method proposed in this study can accelerate the process of reporting traditional human loss information between multiple levels and departments and assess human loss in a real-time and dynamic manner. The findings are important for providing timely assistance to official agencies and the public.

Social media generate a massive amount of information each day. This information is usually generated by people and may be used for many studies. Social media mining is a growing discipline inside data mining, and the results have proven to be quite revealing. Getting the data to work with might seem to be the easiest task in the process, but it can be very challenging for people without programming knowledge. Thus, there are numerous ways to extract information from social media, such as to use the network API, a Web scraper or specialized libraries. Using a straightforward and a cross social media query language we can hide the complexity of those mechanisms and gather information in a more efficient and easier way. This is because many social media share common elements, so we can create and unify queries to search, find and extract information from those platforms. In this paper, we propose a domain-specific query language, specially designed to allow developers or domain experts to extract data from different social media. With this language we unify and simplify the mechanisms of data extraction from social networks such as Twitter and Facebook.

Social media has generated a wealth of data. Billions of people tweet, sharing, post, and discuss everyday. Due to this increased activity, social media platforms provide new opportunities for research about human behavior, information diffusion, and influence propagation at a scale that is otherwise impossible. Social media data is a new treasure trove for data mining and predictive analytics. Since social media data differs from conventional data, it is imperative to study its unique characteristics. This work investigates data collection bias associated with social media. In particular, we propose computational methods to assess if there is bias due to the way a social media site makes its data available, to detect bias from data samples without access to the full data, and to mitigate bias by designing data collection strategies that maximize coverage to minimize bias. We also present a new kind of data bias stemming from API attacks with both algorithms, data, and validation results. This work demonstrates how some characteristics of social media data can be extensively studied and verified and how corresponding intervention mechanisms can be designed to overcome negative effects. The methods and findings of this work could be helpful in studying different characteristics of social media data.

With the rapid growth of location-based social networks (LBSNs), point-of-interest (POI) recommendation has become an important research problem. As one of the most representative social media platforms, Twitter provides various real-life information for POI recommendation in real time. Despite that POI recommendation has been actively studied, tweet images have not been well utilized for this research problem. State-of-the-art visual features like convolutional neural network (CNN) features have shown significant performance gains over the traditional bag-of-visual-words in unveiling the image's semantics. Unfortunately, they have not been employed for POI recommendation from social websites. Hence, how to make the most of tweet images to improve the performance of POI recommendation and visualization remains open. In this paper, we thoroughly study the impact of tweet images on POI recommendation for different POI categories using various visual features. A novel topic model called social media Twitter-latent Dirichlet allocation (SM-TwitterLDA) which jointly models five Twitter features, (i.e., text, image, location, timestamp and hashtag) is designed to discover POIs from the sheer amount of tweets. Moreover, each POI is visualized by representative images selected on three predefined criteria. Extensive experiments have been conducted on a real-life tweet dataset to verify the effectiveness of our method.

This paper aims to address the assessment the similarity between documents or pieces of documents. For this purpose we have developed CASISS (CAlculation of SImilarity of Semi-Structured documents) method to quantify how two given texts are similar. The method can be employed in wide area of applications including content reuse detection which is a hot and challenging topic. It can be also used to increase the accuracy of the information retrieval process by taking into account not only the presence of query terms in the given document (Content Only search — CO) but also the topology (position continuity) of these terms (based on Content And Structure Search — CAS). Tracking the origin of the information in social media, copy right management, plagiarism detection, social media mining and monitoring, digital forensic are among other applications require tools such as CASISS to measure, with a high accuracy, the content overlap between two documents. CASISS identify elements of semi-structured documents using elements descriptors. Each semi-structured document is pre-processed before the extraction of a set of elements descriptors, which characterize the content of the elements.

User-generated travelogues have contributed abundant location representative information (e.g. attracting scenic spots, activities, and local customs), which can greatly facilitate people in trip planning and destination understanding applications. Existing work on location information extraction from user-generated travelogues has primarily focused on the contents, while in this work, we resolve both the contents and structures of travelogues, as well as investigating the interplay of the two. We propose a two-part framework to mine location representative knowledge from travelogues. The first part resolves travelogues in a geographic view. It discovers real location entities subordinated to travel destinations, then decomposes travelogues to acquire corresponding descriptions for each of these entities. Built upon the results of the first part, the second part performs content resolution in a semantic view. By extracting location characterizing concepts and the relatedness among them, it can form a representative concept network for each location entity. Based on a large collection of travelogues, the proposed framework is evaluated using both objective and subjective evaluation methods and shows promising results.

Social online media increasingly emerge as important informal information sources that can contribute to the detection of trends and early warnings in critical fields such as public health monitoring or emergency management. In the face of global environmental challenges the utilization of this information in ecological monitoring contexts has been called for, but examples remain sparse. This can be attributed to the significant technical challenges in processing this data and concerns about the quality, reliability and applicability of information mined from social media to the ecological domain. Here the strength and weaknesses of social media mining for ecological monitoring are assessed using the micro-blogging service Twitter and invasive alien species (IAS) monitoring as an example. The assessment is based on a manual analysis of 2842 Tweets sampled from Twitter data with potential direct or descriptive references to IAS impacting forest ecosystems, which was collected over a period of nearly three years. The results are presented as information topologies for Twitter messages of observational and non-observational character for three IAS with distinctive characteristics (Oak Processionary Moth, Emerald Ash Borer, Eastern Grey Squirrel). The results show that the social media channel Twitter is a rich source of primary and secondary observational biodiversity information. It also provides useful insights in the topical landscape of public communications on IAS as well as the public perception of IAS and IAS management. The analysis suggests broad application opportunities in IAS monitoring and management, and points at applications for related environmental questions. The results highlight that social media mining for ecological monitoring needs to be approached with the same best practices as ecological monitoring in general, requiring a good understanding of the monitored subjects and specific monitoring questions. The challenges in utilizing this information for operational systems are of technical rather than conceptual nature and include extending the degree of automation, especially with regard to image recognition and the automatic provisioning of location information.

Our goal is to summarise and aggregate information from social media regarding the symptoms of a disease, the drugs used and the treatment effects both positive and negative. To achieve this we first apply a supervised machine learning method to automatically extract medical concepts from natural language text. In an environment such as social media, where new data is continuously streamed, we need a methodology that will allow us to continuously train with the new data. To attain such incremental re-training, a semi-supervised methodology is developed, which is capable of learning new concepts from a small set of labelled data together with the much larger set of unlabelled data. The semi-supervised methodology deploys a conditional random field (CRF) as the base-line training algorithm for extracting medical concepts. The methodology iteratively augments to the training set sentences having high confidence, and adds terms to existing dictionaries to be used as features with the base-line model for further classification. Our empirical results show that the base-line CRF performs strongly across a range of different dictionary and training sizes; when the base-line is built with the full training data the $F_1$ score reaches the range 84\%--90\%. Moreover, we show that the semi-supervised method produces a mild but significant improvement over the base-line. We also discuss the significance of the potential improvement of the semi-supervised methodology and found that it is significantly more accurate in most cases than the underlying base-line model.

This study suggests a social media mining approach for identifying time-evolving product opportunities for product improvement, customer complaint management, and competitive intelligence via event detection and tracking (EDT) and sentiment analysis. This approach applies an aging theory-based EDT algorithm to online product reviews to detect the creation of customer-stated events as groups of similar reviews and track their growth and extinction. Next, the approach uses sentiment analysis and an opportunity algorithm to evaluate time-evolving events and provides quantified clues regarding product-development directions based on events with high opportunity. To show the workings of the proposed approach, a case study involving smart speakers is presented. We expect that the approach will contribute to identifying time-evolving product opportunities from large-scale social-media data in addition to enabling the real-time monitoring of customer needs in rapidly evolving product environments.

Various social media mining approaches were adopted for analyzing MOOC learning.The daily, weekly, and monthly trends of MOOC-related tweets were investigated.Sentiment analysis indicated mixed public opinion toward MOOCs.The influencers of sentimental retweets about MOOCs were identified. Because many massive open online courses (MOOCs) have adopted social media tools for large student audiences to co-create knowledge and engage in collective learning processes, this study adopted various social media mining approaches to investigate Twitter messages related to MOOC learning. The first approach adopted in this study was calculating the important descriptive statistics of MOOC-related tweets and examining the daily, weekly, and monthly trends of MOOC that appeared on Twitter. This information can enable MOOC practitioners to observe participants' temporal activities on social media and ascertain the most effective time to post or analyze tweets. Secondly, we investigated how public sentiment toward MOOC learning can be assessed according to related tweets. Because the availability and popularity of opinion-rich social networking services are increasing for MOOC communities, our findings from the sentiment analysis of Twitter data can afford substantial insights into participant perceptions of MOOC learning. Third, we analyzed the positive and negative retweets related to MOOCs and identified the influencers of these retweets. Social network diagrams were also developed to reveal how sentimental messages about MOOCs on Twitter were disseminated from the top influencers with the highest number of positive/negative retweets about MOOCs. Analyzing the relationships among top retweet users is vital to MOOC practitioners because they can use this information to filter or recommend MOOC-related messages to the influencers. In short, the findings pertaining social media mining in this study afford a holistic understanding of MOOC trends, public sentiment toward MOOC learning, and the influencers of MOOC-related retweets.

Evolutionary Algorithms (EA) have been developing rapidly as a powerful and general learning approach which has been used successfully to find a reasonable solution for data mining and knowledge discovery. Genetic algorithm (GA) is a kind of mainstream EA paradigm with a purpose of developing solutions for optimization problems. Clustering ensembles have emerged as an outstanding algorithm in machine learning to leverage the consensus across multiple clustering solutions and combines their predictions into a single solution with improved robustness, stability and accuracy. Multimedia advancement and popularity of the social Web has collectively provided an easy way to generate bulk of videos. Categorization of such Web videos has become a hot research challenge. In this paper, we propose a Semi-supervised Evolutionary Ensemble (SS-EE) framework for social media mining, e.g., Web Video Categorization (WVC), using their low cost textual features, intrinsic relations and extrinsic Web support. The contributions of this research work are as follows. First, we extend the traditional Vector Space Model (VSM) to Semantic VSM (S-VSM) by considering the semantic similarity between the feature terms using Normalized Google Distance (NGD) approach. Second, we define a new distance measure, Triangular Similarity (TrS) between two Textual Feature Vectors (TFV) based on the frequencies of most relevant terms in each category. Third, we iterate the clustering ensemble process with the help of GA guided by a new measure, Pre-Paired Percentage (PPP), to be used as the fitness function during the genetic cycle. Fourth, in the key steps of the GA, crossover and mutation genetic operators, we define them by an intelligent mechanism of clustering ensemble. Fifth, in order to terminate the genetic cycle, we define another new measure, Clustering Quality (Cq), based on similarity matrix and clustering labels. Experiments on real world social-Web data (YouTube) have been performed to validate the SS-EE framework.

The summarization is desirable to efficiently apprehend the gist of the huge amount of data and becomes a significant challenge in many applications such as news article summarization and social media mining. Considering the summaries from multi-documents of one topic can describe various aspects of one given topic, this paper attempts to exploit appropriate priors to generate topic aspect-oriented summarization (abbreviated as TAOS). The underlying intuition of the proposed TAOS is that different topics can prefer different aspects and the different aspects can be represented by different preference of features(e.g., technical topic may prefer proper noun than sports topic). In order to materialize the intuition of TAOS, we first extract several groups of features according to topic factors, and then a group norm penalty (i.e., l 1 / l 2 norm) and latent variables are utilized to select overlapping groups of features. We compare our proposed approach with some state-of-the-art methods on DUC2003, DUC2004 datasets for text summarization and NUS-Wide dataset for image summarization. The results show our method can generate meaningful summarization in terms of ROUGE and Jensen–Shannon Divergence metrics.

Forest monitoring captures human impacts and other biotic and abiotic influences on forests and is a prerequisite for the sustainable use and protection of forest ecosystems. Forest inventories for ...

Recent advances in computer vision on the one hand, and imaging technologies on the other hand, have opened up a number of interesting possibilities for robust 3D scene labeling. This paper presents contributions in several directions to improve the state-of-the-art in RGB-D scene labeling. First, we present a novel combination of depth and color features to recognize different object categories in isolation. Then, we use a context model that exploits detection results of other objects in the scene to jointly optimize labels of co-occurring objects in the scene. Finally, we investigate the use of social media mining to develop the context model, and provide an investigation of its convergence. We perform thorough experimentation on both the publicly available RGB-D Dataset from the University of Washington as well as on the NYU scene dataset. An analysis of the results shows interesting insights about contextual object category recognition, and its benefits.

This paper addresses how Twitter can be used for identifying conflict between communities of users. We aggregate documents by topic and by community and perform sentiment analysis, which allows us to analyze the overall opinion of each community about each topic. We rank the topics with opposing views (negative for one community and positive for the other). For illustration of the proposed methodology we chose a problem whose results can be evaluated using news articles. We look at tweets for republican and democrat congress members for the 112th House of Representatives from September to December 2013 and demonstrate that our approach is successful by comparing against articles in the news media.

In this introduction, we present an overview of the current state of research in the Natural Language Processing tasks of subjectivity and sentiment analysis, as well as their application domains and closely-related research field of emotion detection. Although many definitions exist for these tasks and the research done within their frame spans over approaches with different objectives, we consider subjectivity analysis to deal with the detection of ''private states'' (opinions, emotions, sentiments, beliefs, speculations) and sentiment analysis as the task of detecting, extracting and classifying opinions and sentiments concerning different topics, as expressed in textual input. After describing the key concepts and research directions in these tasks, we present the main achievements obtained so far and the issues that remain to be tackled. Subsequently, we introduce each of the papers in this volume and present their contribution to the research areas of subjectivity and sentiment analysis. Finally, we conclude on the present state of work in these fields and reflect on the possible future developments.

Many web applications today thrive on offering services for large-scale multimedia data, e.g., Flickr for photos and YouTube for videos. However, these data, while rich in content, are usually sparse in textual descriptive information. For example, a video clip is often associated with only a few tags. Moreover, the textual descriptions are often overly specific to the video content. Such characteristics make it very challenging to discover topics at a satisfactory granularity on this kind of data. In this paper, we propose a generative probabilistic model named Preference-Topic Model (PTM) to introduce the dimension of user preferences to enhance the insufficient textual information. PTM is a unified framework to combine the tasks of user preference discovery and document topic mining together. Through modeling user-document interactions, PTM cannot only discover topics and preferences simultaneously, but also enable them to inform and benefit each other in a unified framework. As a result, PTM can extract better topics and preferences from sparse data. The experimental results on real-life video application data show that PTM is superior to LDA in discovering informative topics and preferences in terms of clustering-based evaluations. Furthermore, the experimental results on DBLP data demonstrate that PTM is a general model which can be applied to other kinds of user-document interactions.