Martin D. Sykora

Real-Time Detection, Tracking, and Monitoring of Automatically Discovered Events in Social Media

We introduce ReDites, a system for realtime event detection, tracking, monitoring and visualisation. It is designed to assist Information Analysts in understanding and exploring complex events as they unfold in the world. Events are automatically detected from the Twitter stream. Then those that are categorised as being security-relevant are tracked, geolocated, summarised and visualised for the end-user. Furthermore, the system tracks changes in emotions over events, signalling possible flashpoints or abatement. We demonstrate the capabilities of ReDites using an extended use case from the September 2013 Westgate shooting incident. Through an evaluation of system latencies, we also show that enriched events are made available for users to explore within seconds of that event occurring.

Mental health surveillance after the terrorist attacks in Paris

www.thelancet.com Vol 387 May 28, 2016 2195 mental health services in aff ected areas. As suggested in other research, early emotional reactions are also predictive of long-term mental health needs, and therefore our approach could assist in the allocation of services over time as well. Moreover, in countries with limited formal surveillance infrastructure, the approach could potentially identify mass trauma and guide emergency care into those areas most affl icted.

A novel surveillance approach for disaster mental health

Background Disasters have substantial consequences for population mental health. Social media data present an opportunity for mental health surveillance after disasters to help identify areas of mental health needs. We aimed to 1) identify specific basic emotions from Twitter for the greater New York City area during Hurricane Sandy, which made landfall on October 29, 2012, and to 2) detect and map spatial temporal clusters representing excess risk of these emotions. Methods We applied an advanced sentiment analysis on 344,957 Twitter tweets in the study area over eleven days, from October 22 to November 1, 2012, to extract basic emotions, a space-time scan statistic (SaTScan) and a geographic information system (QGIS) to detect and map excess risk of these emotions. Results Sadness and disgust were among the most prominent emotions identified. Furthermore, we noted 24 spatial clusters of excess risk of basic emotions over time: Four for anger, one for confusion, three for disgust, five for fear, five for sadness, and six for surprise. Of these, anger, confusion, disgust and fear clusters appeared pre disaster, a cluster of surprise was found peri disaster, and a cluster of sadness emerged post disaster. Conclusions We proposed a novel syndromic surveillance approach for mental health based on social media data that may support conventional approaches by providing useful additional information in the context of disaster. We showed that excess risk of multiple basic emotions could be mapped in space and time as a step towards anticipating acute stress in the population and identifying community mental health need rapidly and efficiently in the aftermath of disaster. More studies are needed to better control for bias, identify associations with reliable and valid instruments measuring mental health, and to explore computational methods for continued model-fitting, causal relationships, and ongoing evaluation. Our study may be a starting point also for more fully elaborated models that can either prospectively detect mental health risk using real-time social media data or detect excess risk of emotional reactions in areas that lack efficient infrastructure during and after disasters. As such, social media data may be used for mental health surveillance after large scale disasters to help identify areas of mental health needs and to guide us in our knowledge where we may most effectively intervene to reduce the mental health consequences of disasters.

Decision Support Systems for Sustainable Logistics: A Review and Bibliometric Analysis

Purpose Decision making in logistics is an increasingly complex task for organizations as these involve decisions at strategic, tactical and operational levels coupled with the triple-bottom line of sustainability. Decision support systems (DSS) played a vital role in arguably solving the challenges associated with decision making in sustainable logistics. The purpose of this paper is to explore the current state of the research in the domain of DSS for logistics while considering sustainability aspects. Design/methodology/approach A systematic review approach using a set of relevant keywords with several exclusion criteria was adopted to identify literature related to DSS for sustainable logistics. A total of 40 papers were found from 1994 to 2015, which were then analyzed along the dimensions of publishing trend, geographic distribution and collaboration, the most influential journals, affiliations and authors as well as the key themes of identified literature. The analysis was conducted by means of bibliometric and text mapping tools, namely BibExcel, gpsvisualizer and VOSviewer. Findings The bibliometric analysis showed that DSS for sustainable logistics is an emerging field; however, it is still evolving but at a slower pace. Furthermore, most of the contributing affiliations belong to the USA and the UK. The text mining and keyword analysis revealed key themes of identified papers. The inherent key themes were decision models and frameworks to address sustainable logistics issues covering transport, distribution and third-party logistics. The most prominent sustainable logistics issue was carbon footprinting. Social impact has been given less attention in comparison to economic and environmental aspects. The literature has adequate room for proposing more effective solutions by considering various types of multi-criteria decision analysis methods and DSS configurations while simultaneously considering economic, environmental and social aspects of sustainable logistics. Moreover, the field has potential to include logistics from wide application areas including freight transport through road, rail, sea, air as well as inter-modal transport, port operations, material handling and warehousing. Originality/value To the best of the authors’ knowledge, this is the first systematic review of DSS for sustainable logistics using bibliometric and text analysis. The key themes and research gaps identified in this paper will provide a reference point that will encourage and guide interested researchers for future study, thus aiding both theoretical and practical advancements in this discipline.

Social media analytics in museums: extracting expressions of inspiration

ABSTRACT Museums have a remit to inspire visitors. However, inspiration is a complex, subjective construct and analyses of inspiration are often laborious. Increased use of social media by museums and visitors may provide new opportunities to collect evidence of inspiration more efficiently. This research investigates the feasibility of a system based on knowledge patterns from FrameNet – a lexicon structured around models of typical experiences – to extract expressions of inspiration from social media. The study balanced interpretation of inspiration by museum staff and computational processing of Twitter data. This balance was achieved by using prototype tools to change a museum’s Information Systems in ways that both enabled the potential of new, social-media-based information sources to be assessed, and which caused the museum staff to reflect upon the nature of inspiration and its role in the relationships between the museum and its visitors. The prototype tools collected and helped analyse Twitter data related to two events. Working with museum experts, the value of finding expressions of inspiration in Tweets was explored and an evaluation using annotated content achieved an F-measure of 0.46, indicating that social media may have some potential as a source of valuable information for museums, though this depends heavily upon how annotation exercises are conducted. These findings are discussed along with the wider implications of the role of social media in museums.

Using geolocated social media for ecological momentary assessments of emotion: Innovative opportunities in psychology science and practice.

Social media applications have become popular methods of online communication, interaction, and social networking. Many people use social media websites and mobile applications, such as Twitter, to create and post personal expressions in public online forums. This online content presents opportunities for using social media as a data source with the potential to improve evaluation of theoretical models of emotional and stressful experiences across various topics and subfields of psychology science and practice. In this article, we discuss emerging information retrieval and analytic methods using social media for ecological momentary assessments of emotion. We describe 2 specific methods we have developed in the context of Twitter and their use in a broader study investigating relationships among people’s emotional experiences, their expressions of experiences in social media, their daily geospatial movements and locations, and their stress experiences. We conclude with a discussion of potential applications and ethical considerations for these methods in professional psychology practice and science. Les applications des médias sociaux sont devenues de populaires moyens de communication, d’interaction et de réseautage social en ligne. Un grand nombre d’utilisateurs des sites Web et des applications mobiles des médias sociaux, tel Twitter, créent des contenus d’expression personnelle qu’ils affichent ensuite sur des forums publics. Ces contenus électroniques donnent la possibilité d’utiliser les médias sociaux comme une source de données servant éventuellement à améliorer l’évaluation des modèles théoriques d’expériences affectives et stressantes dans divers domaines et sous-domaines de la science et de la pratique de la psychologie. Dans le présent article, nous examinons de nouvelles méthodes de récupération et d’analyse de l’information, basées sur l’utilisation des médias sociaux, pour effectuer des évaluations écologiques momentanées des émotions. Nous décrivons deux méthodes particulières, que nous avons élaborées dans le contexte de Twitter, et leur utilisation dans une étude plus générale sur les liens existant entre les expériences affectives des personnes, le récit de leurs expériences dans les médias sociaux, leurs déplacements et emplacements géographiques quotidiens et leurs expériences en matière de stress. Nous terminons par une discussion sur les éventuelles applications de ces méthodes dans la science et la pratique de la psychologie et les considérations éthiques inhérentes à ces applications.

Personal Activity Centres and Geosocial Data Analysis: Combining Big Data with Small Data

Understanding how people move and interact within urban settings has been greatly facilitated by the expansion of personal computing and mobile studies. Geosocial data derived from social media applications have the potential to both document how large segments of urban populations move about and use space, as well as how they interact with their environments. In this paper we examine spatial and temporal clustering of individuals’ geosocial messages as a way to derive personal activity centres for a subset of Twitter users in the City of Toronto. We compare the two types of clustering, and for a subset of users, compare to actual self-reported activity centres. Our analysis reveals that home locations were detected within 500 m for up to 53% of users using simple spatial clustering methods based on a sample of 16 users. Work locations were detected within 500 m for 33% of users. Additionally, we find that the broader pattern of geosocial footprints indicated that 35% of users have only one activity centre, 30% have two activity centres, and 14% have three activity centres. Tweets about environment were more likely sent from locations other than work and home, and when not directed to another user. These findings indicate activity centres defined from Twitter do relate to general spatial activities, but the limited degree of spatial variability on an individual level limits the applications of geosocial footprints for more detailed analyses of movement patterns in the city.

Big data opportunities for social behavioral and mental health research

This paper was published in the journal Social Science and Medicine and the definitive published version is available at https://doi.org/10.1016/j.socscimed.2017.07.018.

Financial news content publishing on youtube.com

Recently a number of academic publications have investigated various properties and dynamics of authors contributors on online Web 2.0 communities. The most intensively examined communities have until now been discussion boards and blogs. In this paper we look at, and identify revealing patterns of content publishers on YouTube. This is the most popular community based service on the world wide web as ranked by the frequency of visited webpages. The research is motivated in terms of gaining better understanding of content publishing habits within financial news topic specifically and we investigate the potential for trend detection in financial markets area. A number of side issues, such as publisher bias and various video properties are also examined. It turns out, the number of video submissions by professional authors has increased considerably in recent months. There is significant quantity to allow statistical analysis of events. As we show, the potential value of the data on YouTube cannot be ignored any longer. We present recent results and work on a project that investigated a completely new dataset, not really considered in previous literature.

Case based reasoning approach for transaction outcomes prediction on currency markets

This paper presents a case based reasoning approach for making profit in the foreign exchange (forex) market with controlled risk using k nearest neighbour (kNN) and improving on the results with neural networks (NNs) and a combination of both. Although many professionals have proven that exchange rates can be forecast using neural networks for example, poor trading strategies and unpredictable market fluctuation can inevitably still result in substantial loss. As a result, the method proposed in this paper will focus on predicting the outcome of potential trades with fixed stop loss (ST) and take profit (TP) positions1, in terms of a win or loss. With the help of the Monte Carlo method, randomly generated trades together with different traditional technical indicators are fed into the models, resulting in a win or lose output. This is clearly a case based reasoning approach, in terms of searching similar past trade setups for selecting successful trades. There are several advantages over classical forecasting associated with such an approach, and the technique presented in this paper brings a novel perspective to problem of exchange trades predictability. The strategies implemented have not been empirically investigated with such wide a range of time granularities as is done in this paper, in any to the authors known academic literature. The profitability of this approach is back-tested at the end of this paper and highly encouraging results are reported.