Internet Science

This paper presents the principles and the design of the WeMake framework. The goal of the WeMake framework is twofold: firstly, to create an interdisciplinary team of experts that together with students/teachers and a new participatory design methodology adapted to embodied interactions will develop low cost and easily reconstructable embodied interaction environments for STEAM domains; and secondly to invite students, teachers and schools across the world to build, exploit, share and assess their own versions of these embodied learning environments. The ultimate goal is to create an infrastructure that will motivate all stakeholders (from researchers to students) and maintain a perpetual cycle of embodied STEAM learning environment proposals and their deployment in the educational practice.

With the advent of the Internet of Things, low-cost sensing technologies are becoming increasingly available, allowing citizens to collectively monitor and share data about the environment. A subset of these technologies is being made at maker spaces, using open source and affordable technologies. While these systems have the potential to power bottom-up participatory data networks, a key concern is that laypeople often fail to effectively setup and connect these sensors to the Internet because they lack technical skills and/or the systems’ user experience is poorly designed. We present a novel onboarding application that aims to facilitate the process of sensor setup and connection by non-experts. It works by providing an integrated design experience, scaffolding the complexity of the process, and guiding the user in a conversational fashion. We hope to inspire other developers and designers to consider the needs of non-technical and diverse communities in the design of IoT systems.

Environmental data is collected at unprecedented scales and speeds, targeting diverse societal challenges, and through the inclusion of multiple stakeholders. Yet, an understanding of enabling technologies involved in the engagement of citizens appear largely outside of the realm of air pollution. Recently, different air pollution projects have been rolled out in Europe and abroad; a structured analysis, however, of the way citizens are involved in these type of projects does not yet exist. In contribution to the ongoing EU-Funded project hackAIR, this paper therefore explores this research gap on the topic of air pollution and citizen science through the following question: Which engagement mechanisms can be identified in existing air pollution citizen science projects? We combine multiple literature sources, employ a systematic case study analysis and conduct seven qualitative interviews with key experts to target citizen science projects related to air pollution. Several mechanisms emerged at the interface between air pollution, citizen participation and knowledge production. These include: (1) Scale, (2) User-involvement and co-creation, (3) Communication, and (4) User motivation and aspects of behaviour. Despite its growing reputation in digital innovation, a majority of the mapped projects do not explicitly engage in any co-creation process. Multiple project insights suggest the importance of non-academic stakeholders as agents for communication and engagement. Campaign-based gamification can prove successful in establishing urgency in local contexts. Common engagement barriers include issues in the data contribution, science communication, technical project limitations, scaling and the critical nature of distributed sensors. This preliminary research offers a fruitful approach in assessing and comparing initiatives, and can enrich our understanding of the contribution that air pollution technology can have in citizen science.

Grassroots initiatives, initiated and managed by local communities, have been spreading in cities all around Europe, addressing the citizens’ needs and the daily challenge of finding sustainable solutions for urban environments about food, waste, transport or energy. In recent years, these communities are increasingly making use of new technologies and some of them are currently shaped around Internet platforms, which became critical to their existence. This paper address them as grassroots online initiatives, aiming to outline their specificities and to discuss the methodology to research their impacts, with a specific attention towards the environmental dimension of their contribution to the society. The analysis is descriptive in nature and it has the main goal of integrating the emerging literature on this topic and of paving the way for further research activities in the field. To reach this objective, it presents a review of how new communication technologies have allowed the development of different kinds of community based initiatives, how these initiatives can be assessed and if they present significant differences with respect to the more traditional, face to face ones, focusing on a selection of case studies around Europe. An in-depth analysis of two initiatives, dealing respectively with sustainable mobility and sustainable food production, allows presenting some main findings.

Diversity and inclusion in the technology sector is increasingly debated, specially in the context of equal opportunities for all and a shortage of experts in many tech related industries. The need to be more inclusive can refer to different age groups, people with diverse culturally and linguistically backgrounds or gender. All in all, ethnic, gender and socio-economic diversity is not yet at the forefront of fabrication laboratories (FabLabs) agendas for change. This paper aims to contribute to the discussion of diversity and inclusion by primarily elaborating gender relations in FabLabs and, to a lesser extent, discussing age and socio-economic conditions of makers. Our analysis is based on 39 interviews and the analysis of 55,450 data points extracted from the log files of 3d-printers, CNC milling machines, laser cutters and cutting plotters. This combination of qualitative and quantitative data reveals that, indeed, some machines are used more frequently by men or women. However, the main difference is in absolute numbers, i.e. women are not joining FabLabs for a variety of reasons ranging from uninviting cultures to the lack of role models in technology driven areas in general.

In this paper, we present some aspects of the European Project InSPIRES, which is focused on the concept of the science shop. A science shop is a methodology of opening universities and research centers to the civil society, accepting proposals for investigations and having them carried out by the students under the supervision and the scientific responsibility of a senior researcher. The goal of InSPIRES is that of cataloguing the methodologies used by the different science shops in the world, extracting the best practices; promoting the development of similar experiences in southern Europe and related countries, and increasing the continuous participation of citizens along the lines of the responsible research and innovation, also using Internet-based tools.

In this paper, we analyse some experiments of extending the practice of the science cafés, a well know participatory methodology of science communication, with the help of the possibilities offered by Internet. We describe the use of a web platform to disseminate the events and the use of YouTube for streaming and podcasting, with a comparison between costs and benefits.We have experimented and analysed several scenarios, from the streaming of traditional science cafés to the dissemination of the results of European projects.

Traditional views on the public value creation focus on the public sector organizations as sole initiators of the value creation processes. The rise of interactive Information and Communication Technologies (ICT), however, opens new opportunities for broader engagement of civic stakeholders in the public value generation. The concept of co-creation is seen as a new framework describing the shift from considering organizations as the definers of the value to a more inclusive and collaborative processes involving the end-users and other external actors. The article proposes a conceptual framework providing holistic integration of current research efforts on the co-creation of public value by focusing on the initiatives originating outside governmental entities. The conceptual framework provides understanding on how ICT-enabled co-creation should be utilized in the generation of the public value.

Governments in the western countries are faced with a number of growing social challenges, such as unemployment, migration, ageing population, explosion of chronic disease. Although they offer a wide range of public social services, we cannot assume that the economy will grow at a rate that can fund expanding needs for services risen by these challenges. We have to find new ways to adapt service provision and prevent social exclusion. Social innovations are new approaches to addressing social needs through engaging beneficiaries and supporting actors in the development of solutions. There is great potential in exploiting digital networks for social innovation. Supporting virtual communities and new forms of collaboration, digital networks make it possible to co-create knowledge and solutions at a wide scale. Various digital social innovation platforms have emerged in the recent years. However we observe that these platforms focus on specific areas, such as open democracy, collaborative consumption or environment, rather than providing support for a wide range of social challenges. We propose to develop a digital social innovation platform that facilitates citizens and organisations to collaboratively develop innovative social solutions. From the analysis of the current innovation processes and the expectations of two distinct cases, Cibervoluntarios (CIB) and Experts-In-Teamwork (EiT), we derive an initial set of concepts that serve as a basis for the development of a methodology and platform for social innovation.

This paper presents two case studies of citizen data collection and dissemination applications, developed for or by three different local authorities in Northern Europe. These case studies highlight the challenges in meeting the goals of Open Data, of involving citizens as sources of information, and of engendering and maintaining trust as a service provider all at the same time. The challenge of making data open can be seen as at odds with protecting the privacy and safety of citizens when it is sourced directly or indirectly from their actions. Encouraging citizens to collect, curate, and submit data can create misguided expectations of influence over the processes of local government, and disillusionment where action or feedback are not forthcoming. A local authority is trusted to provide information that is verified and for which it is accountable. Balancing this with goal of disseminating the results of citizen sourced data collection activities can result in frustration for developers, users, and local authority employees. In response to these issues this paper presents the following four design opportunities: probabilistic and personalised representations of data, making accountable the use of collected data, respecting the boundaries of data, and designing for the graceful degradation of resources.

Embeddedness of politicians and political organizations in a discussion defines its level of institutionalization and creates a public arena for collaboration between publics and institutional actors. Thus, testing whether traditional hierarchies (in terms of presence of politically institutionalized actors) show up in online discussions deserves scholarly research. Moreover, it is also important to see whether more democratic societies show patterns of public involvement of politically institutionalized users that would differ from those in more authoritarian contexts.To assess the ‘influencer’ status of politically institutionalized actors on Twitter cross-culturally, we have selected conflictual Twitter discussions in Germany, the USA, and Russia, all based on violent inter-ethnic clashes. Using vocabulary-based web crawling, we collected data on them and formed samples of top users selected by four activity metrics and five network metrics, to assess the positions of political users in the top lists and correlations of user status with their top list ranks. To this, we added qualitative assessment of presence of political users in comparative perspective.Our results show that, in all the cases, presence of political actors in online discussions is scarce; also, political actors tend to fail to link user groups or stay in the center of discussion. There is also meaningful divergence of Russia from the pattern that Germany and the USA show: while in these countries politicians gain user attention based on content, in Russia it is the status itself that matters, and political users tend to gain weight in the discussion structure despite low attention levels.

Decisions on environmental topics taken today are going to have long-term consequences that will affect future generations. Young people will have to live with the consequences of these decisions and undertake special responsibilities. Moreover, as tomorrow’s decision makers, they themselves should learn how to negotiate and debate issues before final decisions are made. Therefore, any participation they can have in environmental decision making processes will prove essential in developing a sustainable future for the community. However, recent data indicate that the young distance themselves from community affairs, mainly because the procedures involved are ‘wooden’, politicians’ discourse alienates the young and the whole experience is too formalized to them. Authorities are aware of this fact and try to establish communication channels to ensure transparency and use a language that speaks to new generations of citizens. This is where STEP project comes in.STEP (www.step4youth.eu) is a digital Platform (web/mobile) enabling youth Societal and Political e-Participation in decision-making procedures concerning environmental issues. STEP is enhanced with web/social media mining, gamification, machine translation, and visualisation features.Six pilots in real contexts are being organised for the deployment of the STEP solution in 4 European Countries: Italy, Spain, Greece, and Turkey. Pilots are implemented with the direct participation of one regional authority, four municipalities, and one association of municipalities, and include decision-making procedures on significant environmental questions.

As an industrial revolution booms in Chile, the country’s air has been flooded by toxic emissions. Urban cities face the worst of the pollution, as factories are booming and urban centers are growing. Indeed, one of the main contributors towards the accumulation of PM2.5 are cars. Sharing trips may help reduce the number of private and public vehicles on the road and cut down on greenhouse gas emissions, travel time and individual costs. In this research I apply the concept of shareability networks to a survey of 113,591 of trips taken in the city of Santiago in Chile, showing that with increasing but still relatively low passenger discomfort, cumulative trip length can be cut by 50% or more. I quantify the benefit of ride sharing in terms of traffic and emission reduction. I finally show that the ride sharing potential is substantial, with nearly 100% of the trips shareable with current public transportation trip demand.

Citizens are shaping their food preferences and expressing their food experiences on a daily basis reflecting their way of living, culture and well-being . In this paper, we focus on food perceptions and experiences in the context of smart citizen and tourist sensing. We analyze Foursquare user reviews about food-related points of interest in ten European cities, and we explore the imprint of a city as it is shaped based on the spatial distribution of food-related topics and sentiments. The topic modelling and sentiment analysis results are visualized using geo-referenced heat maps that enrich the cities maps with information that allows for a more insightful navigation across their different geographical regions providing insights not available in the original data.

Supporting the use of technology into industrial environments is an issue of mass appeal within the Industry 4.0 initiative, with a lot of promising research especially into interaction, production and training sections. In this paper, a Social Collaboration platform is introduced which creates an online community for workers as well as an Augmented Reality (AR) tool for production and training purposes both of which constitute gamified applications on which a customizable Gamification platform is applied according to impending needs. These tools have been implemented in order to become of daily use to employees in factories and incentivize them to promote collaboration, engagement, participation and work satisfaction. Every promoted industrial behavior can be described and awarded based on the offered rule engine. Thus, two gamified processes are offered regarding Social Collaboration and AR training to employees of industrial environments, so that an inference is drawn concerning participation, satisfaction and self-fulfillment. The use of the platforms is illustrated in this paper by two examples consisting one use case for a section in social collaboration and a second use case of training through AR.

Following the invention and proliferation of the Internet, Web and mobile technologies, we have seen a global revolution in retailing. Despite the rapid growth of e-commerce, the online grocery shopping market has taken until now to gain traction, currently constituting 6.9% of the UK’s grocery market, but projected to increase 68.3% to £17.6 bn by 2021. There is little work accounting for new and contingent behaviours in the online grocery market, not least because of historically poor access to retailers’ data. This paper leverages access to the UK’s fourth largest supermarket, WM Morrisons Plc (Morrisons) to investigate consumer behaviour in this market, augmenting the Office for National Statistics’ Living Costs and Food Survey, the UK’s only substantial publicly available resource to date. This paper establishes that there have been changes in consumer behaviours in response to the unique opportunities and challenges of online grocery shopping and explores the specific socio-technical factors that may be contributing to these changes, namely: ease of price comparison; attitudes to purchasing perishable goods online; and logistical considerations. Furthermore, it provides some evidence that the proportion of fresh products bought online exceeds the proportion bought offline, contrary to popular belief. Finally, this paper argues that with correction for location bias, the Morrisons sample could provide a proxy for examining online grocery behaviour in-depth at the national level.

An increasing computing capability is raising the opportunities to use a large amount of publicly available data for creating new applications and a new generation of public services.But while it is easy to find some early examples of services concerning control systems (e.g. traffic, meteo, telecommunication) and commercial applications (e.g. profiling systems), few examples are instead available about the use of data as a new resource for empowering citizens, i.e. supporting citizens’ decisions about everyday life, political choices, organization of their movements, information about social, cultural and environmental opportunities around them and government choices. Developing spaces for enabling citizens to harness the opportunities coming from the use of this new resource, offers thus a substantial promise of social innovation.This means that open data is virtually a new resource that could become a new commons with the engagement of interested and active communities. The condition for open data becoming a new commons is that citizens become aware of the potential of this resource, that they use it for creating new services and that new practices and infrastructures are defined, that would support the use of such resource.

Involving users in the design of sharing economy services is important to realize the expected growth in this market. However, such involvement may be challenging due to the complexity and networked character of the service context. We present a case study showing how users’ online feedback on novel design concepts may represent a viable approach to user involvement. In particular, the feedback provides insight into the strengths and weaknesses of proposed concepts as well as suggestions of relevance to the subsequent design process. On the basis of the case study, lessons learnt are discussed, as is needed future research.

Since the 1992 Earth Summit, 4.4 billion people or 64% of the world’s population have been affected by disasters and the number of crisis has more than doubled [8, 15]. In a world where disasters strike more frequently and with more intensity, governments and emergency services have a strong incentive to increase efficiency and resilience of information systems used to plan or to manage the crises. The SecInCoRe project, financed by the European Union under the FP7 Security framework, draws a socio-technical concept of a Common Information Space (CIS) to solve the most urgent challenges faced by emergency services and first responders. Among others: enhancing interoperability and communication within different organisations at national and at European level, promoting the involvement and participation of the users in line with what is requested by Next Generation Internet Initiative. In parallel to the CIS concept design, the project developed a strategy for the validation and evaluation of the project components and concepts through the use of a CIS Demonstrator. The SecInCoRe Validation and Evaluation Strategy (VES) is based on a combined approach which integrates elements of the E-OCVM methodology [6] with the SEQUOIA methodology [11]. This paper presents the strategy that was used to validate and evaluate the SecInCoRe outcomes and its results. The aim is to report on the feedback of users from emergency services to make clear how and why a socio-technical system as the CIS could help them in the management of a crisis.

Fog computing is an emerging technology for the Internet of Things (IoT) that aims to support processing on resource-constrained distributed nodes in between the sensors and actuators on the ground and compute clusters in the cloud. Fog Computing benefits from low latency, location awareness, mobility, wide-spread deployment and geographical distribution at the edge of the network. However, there is a need to investigate, optimise for and measure the performance, scalability and interoperability of resource-constrained Fog nodes running real-time applications and queries on streaming IoT data before we can realise these benefits. With Eywa, a novel Fog Computing infrastructure, we (1) formally define and implement a means of distribution and control of query workload with an inverse publish-subscribe and push mechanism, (2) show how data can be integrated and made interoperable through organising data as Linked Data in the Resource Description Format (RDF), (3) test if we can improve RDF Stream Processing query performance and scalability over state-of-the-art engines with our approach to query translation and distribution for a published IoT benchmark on resource-constrained nodes and (4) position Fog Computing within the Internet of the Future.

During the last years, citizens and transparency initiatives put increasing pressure on governments, organizations, and companies to be more transparent and to publicize information pertaining to their operations. Although several organizations have started engaging in open data practices, data quality, structure and availability is still highly inconsistent across organizations, which makes it challenging and effort-intensive to obtain and analyze large-scale high-quality datasets. To this end, this paper examines how publicly available financial and corporate data can be leveraged to extract useful inferences regarding the financial and social performance of companies. Numerous reports have been collected from the Securities Exchange Commission (SEC) and analyzed to study hypotheses regarding the corporate practices and social responsibility of companies.

Personalization of online content creates filter bubbles and reinforces echo chambers. These are driven not only by natural human behaviours but also by design choices and efficiency-driven recommender systems. The traditional media policy goal of exposing citizens to diverse information to protect pluralism has not found its concrete application on social media. As the usage of social media as a news source increases, as well as personalization’ sophistication and group polarization, there is a need for preventing audience fragmentation. The paper suggests serendipity as a potential design principle and, eventually, policy goal. Indeed, serendipity – considered both as a capability and a process of seeking and processing unexpected and valuable information – requires diverse information as a precondition and it causes cognitive diversity. Serendipity as a design principle might encompass fundamental phases of production and consumption of information, representing a positive freedom valuable from an epistemological, psychological and political perspective. With serendipity being both limited and cultivated in the digital environment, the research reveals a theoretical trade-off between relevance and serendipity (or unknown relevance) that might be tackled with serendipity-driven recommender systems and structural and informational nudging. Such approach could turn the media policy goal of exposing users to diverse information towards an experience of diversity that comes through an architecture for serendipity.

Public mailing lists, such as the mailing lists used by the IETF for Internet Standardization, can be used as big real world data set for analysis of social interactions. However, volatile participation and the usage of mail addresses as changeable pseudonyms constitute a challenge for data mining in these data. We conducted a case study of mailing list analysis wherein we address the consistent identification of a person with all of her contributions to be used as panel data. Based on the postings of individuals on different mailing lists, correlations between standardization areas in the IETF groups can be computed. Isolated and meshed standardization areas can be identified.

Linked Data is an emerging paradigm of publishing data in the Internet, accompanied with semantic annotations in a machine understandable fashion. The Internet provides vast data, useful in identifying Public Health trends, e.g. concerning the use of drugs, or the spread of diseases. Current practice of exploiting such data includes their combination from different sources, in order to reinforce their exploitation potential, based on unstructured data management practices and the Linked Data paradigm. In this paper, we present the design, the challenges and an evaluation of a Linked Data model to be used in the context of a platform exploiting social media and bibliographic data sources (namely, Twitter and PubMed), focusing on the application of Adverse Drug Reaction (ADR) signal identification. More specifically, we present the challenges of exploiting Bio2RDF as a Linked Open Data source in this respect, focusing on collecting, updating and normalizing data with the ultimate goal of identifying ADR signals, and evaluate the presented model against three reference evaluation datasets.

While public finance data are becoming openly available as part of the broader promotion of fiscal transparency, there is little effort towards maximizing their potential value by interlinking them under a concrete framework and establishing the means to extract interesting insights. The Linked Open Economy model (LOE) aims to act as a top-level conceptualization that connects economic flows with open economic data and as an adaptable and extensible underlying model for modelling different scenarios. The paper presents the LOE model, emphasizing its theoretical foundations. Furthermore, it presents the usage of the model in realistic settings, showcasing its extensibility and its ability to address interesting questions.

Nowadays, a large amount of text documents are produced on a daily basis, so we need efficient and effective access to their content. News articles, blogs and technical reports are often lengthy, so the reader needs a quick overview of the underlying content. To that end we present graph-based models for keyword extraction, in order to compare the Bag of Words model with the Graph of Words model in the keyword extraction problem. We compare their performance in two publicly available datasets using the evaluation measures Precision@10, mean Average Precision and Jaccard coefficient. The methods we have selected for comparison are grouped into two main categories. On the one hand, centrality measures on the formulated Graph-of-Words (GoW) are able to rank all words in a document from the most central to the less central, according to their score in the GoW representation. On the other hand, community detection algorithms on the GoW provide the largest community that contains the key nodes (words) in the GoW. We selected these methods as the most prominent methods to identify central nodes in a GoW model. We conclude that term-frequency scores (BoW model) are useful only in the case of less structured text, while in more structured text documents, the order of words plays a key role and graph-based models are superior to the term-frequency scores per document.

Implicit Interaction takes advantage of the rise of predictive algorithms, trained on our behaviour over weeks, months and years, and employs them to streamline our interactions with devices from smartphones to Internet connected appliances. Implicit Interaction provides users the advantage of systems that learn from their actions, while giving them the feedback and controls necessary to both understand and influence system behaviour without having to rely on an application for every connected device. This is an active area of research and as such presents challenges for interaction design due, in part, to the use of user-facing machine learning algorithms. This paper discusses the challenges posed by designing in accountability for system actions and predictions, the privacy concerns raised by both the sensing necessary to power these predictions and in how the predictions and systems actions themselves can expose behavioural patterns, and the challenges inherent in designing for the reality of machine learning techniques rather than the hype.

The paper describes a technical demonstration of an open-source framework for monitoring, analysis and search over multiple social media platforms. The framework is intended to be a valuable tool for media intelligence professionals, as well as a framework and testbed for scientists and developers with interest in social media research.

“Reputation systems” are widely used in e-commerce, crowdsourcing and crowdfunding platforms, as well as in a multitude of different web-based services. However, recent works stressed how the attribution of the reputation could be unrelated to the actual behaviour of the users. The aim of this study was to investigate which factors influenced the formation and the maintenance of the reputation in an online multiplayer game. Our study provided further and novel evidence of how people greatly rely on the previous acquired reputation of their interactors, whenever they are asked to rate them after a game’s interaction. The “Reputational heuristics” adopted by players appeared to neglect the actual interactor’s behaviour, in favor of a judgement in accordance with his behaviour.

There is a growing interest in chatbots, which are machine agents serving as natural language user interfaces for data and service providers. However, no studies have empirically investigated people’s motivations for using chatbots. In this study, an online questionnaire asked chatbot users (N = 146, aged 16–55 years) from the US to report their reasons for using chatbots. The study identifies key motivational factors driving chatbot use. The most frequently reported motivational factor is “productivity”; chatbots help users to obtain timely and efficient assistance or information. Chatbot users also reported motivations pertaining to entertainment, social and relational factors, and curiosity about what they view as a novel phenomenon. The findings are discussed in terms of the uses and gratifications theory, and they provide insight into why people choose to interact with automated agents online. The findings can help developers facilitate better human–chatbot interaction experiences in the future. Possible design guidelines are suggested, reflecting different chatbot user motivations.

Online social network platforms have served as a substantial venue for research, offering a plethora of data that can be analysed to cultivate insights about the way humans behave and interact within the virtual borders of these platforms. In addition to generating content, these platforms provide the means to spread content via built-in functionalities. The traces of the spreading content and the individuals’ incentives behind such behaviour are all parts of a phenomenon known as information diffusion. This phenomenon has been extensively studied in the literature from different perspectives, one of which is cascades: the traces of the spreading content. These traces form structures that link users to each other, where these links represent the direction of information flow between the users. In fact, cascades have served as an artefact to study the information diffusion processes on online social networks. In this paper, we present a survey of cascades; we consider their definitions and significance. We then look into their topology and what information is used to construct them and how the type of content and the platform can consequently affect cascades’ networks. Additionally, we present a survey of the structural and temporal features of cascades; we categorise them, define them and explain their significance, as these features serve as quantifiers to understand and overcome the complex nature of cascades.

We propose a data-based approach to doing ethnographic research in a digital environment. It has three main components. First, it treats online conversational environments as human communities, that ethnographers can engage with as they would in onsite fieldwork. Second, it represents those conversations, and the fieldnotes made by researchers thereon, in network form. We call these networks semantic social networks, as they incorporate information on social interaction and their meaning. They encode a map of the associations between key concepts as perceived by informants as a group. Third, it uses methods borrowed from network science to process these data.We present an application of this method to a large online conversation about community provision of health and social care, and discuss its potential for harnessing collective intelligence.

Large amounts of social media posts are produced on a daily basis and monitoring all of them is a challenging task. In this direction we demonstrate a topic detection and visualisation tool in Twitter data, which filters Twitter posts by topic or keyword, in two different languages; German and Turkish. The system is based on state-of-the-art news clustering methods and the tool has been created to handle streams of recent news information in a fast and user-friendly way. The user interface and user-system interaction examples are presented in detail.

The statistics presented by the World Health Organization inform that 90% of the suicides can be attributed to mental illnesses in high-income countries. Besides, previous studies concluded that people with mental illnesses tend to reveal their mental condition on social media, as a way of relief. Thus, the main objective of this work is the analysis of the messages that a user posts online, sequentially through a time period, and detect as soon as possible if this user is at risk of depression. This paper is a preliminary attempt to minimize measures that penalize the delay in detecting positive cases. Our experiments underline the importance of an exhaustive sentiment analysis and a combination of learning algorithms to detect early symptoms of depression.