Search

We define and solve the problem of event detection and delineation as a task of identifying events and decomposing them to their major sub-events, with a description and a timeline. We propose DeLi, an algorithm that focuses on providing such an understanding of events and sub-events. DeLi, to the best of our knowledge, is the first method that addresses the problem in a generic stream of text, and in an online fashion. Extensive evaluation on social streaming data demonstrates that, by combining the structure of a social network with content attributes, our method outperforms the state-of-the-art techniques.

Social networks have become the de facto online resource for people to share, comment on and be informed about events pertinent to their interests and livelihood, ranging from road traffic or an illness to concerts and earthquakes, to economics and politics. This has been the driving force behind research endeavors that analyze such data. In this paper, we focus on how Content Networks can help us identify events effectively. Content Networks incorporate both structural and content-related information of a social network in a unified way, at the same time, bringing together two disparate lines of research: graph-based and content-based event discovery in social media. We model interactions of two types of nodes, users and content, and introduce an algorithm that builds heterogeneous, dynamic graphs, in addition to revealing content links in the network's structure. By linking similar content nodes and tracking connected components over time, we can effectively identify different types of events. Our evaluation on social media streaming data suggests that our approach outperforms state-of-the-art techniques, while showcasing the significance of hidden links to the quality of the results.

Twitter is one of the most prominent social media platforms nowadays. A primary reason that has brought the medium at the spotlight of academic attention is its real-time nature, with people constantly uploading information regarding their surroundings. This trait, coupled with the service’s data access policy for researchers and developers, has allowed the community to explore Twitter’s potential as a news reporting tool. Finding out promptly about newsworthy events can prove extremely useful in crisis management situations. In this paper, we explore the use of Twitter as a mechanism used in disaster relief, and consequently in public safety. In particular, we perform a case study on the floods that occurred in the United Kingdom during January 2014, and how these were reflected on Twitter, according to tweets (i.e., posts) submitted by the users. We present a systematic algorithmic analysis of tweets collected with respect to our use case scenario, supplemented by visual analytic tools. Our objective is to identify meaningful and effective ways to take advantage of the wealth of Twitter data in crisis management, and we report on the findings of our analysis.

Social media analysis constitutes a scientific field that is rapidly gaining ground due to its numerous research challenges and practical applications, as well as the unprecedented availability of data in real time. Several of these applications have significant social and economical impact, such as journalism, crisis management, advertising, etc. However, two issues regarding these applications have to be confronted. The first one is the financial cost. Despite the abundance of information, it typically comes at a premium price, and only a fraction is provided free of charge. For example, Twitter, a predominant social media online service, grants researchers and practitioners free access to only a small proportion (1%) of its publicly available stream. The second issue is the computational cost. Even when the full stream is available, off the shelf approaches are unable to operate in such settings due to the real-time computational demands. Consequently, real world applications as well as research efforts that exploit such information are limited to utilizing only a subset of the available data. In this paper, we are interested in evaluating the extent to which analytical processes are affected by the aforementioned limitation. In particular, we apply a plethora of analysis processes on two subsets of Twitter public data, obtained through the service’s sampling API’s. The first one is the default 1% sample, whereas the second is the Gardenhose sample that our research group has access to, returning 10% of all public data. We extensively evaluate their relative performance in numerous scenarios.

Browsing the web is one of the most common activities that users engage in nowadays, and downloading web resources of interest, such as images, documents, music, etc., is part of this process. However, users would rather temporarily save that resource to a default path that they have easy access to (e.g. their “Desktop”) than select the actual directory where they would eventually place it. This clearly implies that existing user interfaces are not as effective for this particular task as the users would like them to be. Instead of proposing a different User Interface, in this paper, we try to address the problem at its core, and propose a methodology to suggest the most likely directory where the file would (eventually) be saved by the user. By doing so, future interfaces can also benefit from our technique. We provide a formal definition of the problem and propose a classification framework to tackle it. We present our overall solution to this problem, namely Directory Download PrediCtor, or DiDoCtor for short. We give experimental evidence of its effectiveness, by implementing our approach as part of a widely used browser and evaluate it with real user activity. We also discuss lessons learned from this process, regarding the efficiency perspective.

Microblogging platforms, such as Twitter, Tumblr etc., have been established as key components in the contemporary Web ecosystem. Users constantly post snippets of information regarding their actions, interests or perception of their surroundings, which is why they have been attributed the term Live Web. Nevertheless, research on such platforms has been quite limited when it comes to identifying events, but is rapidly gaining ground. Event identification is a key step to news reporting, proactive or reactive crisis management at multiple scales, efficient resource allocation, etc. In this paper, we focus on the problem of automatically identifying events as they occur, in such a user-driven, fast paced and voluminous setting. We propose a novel and natural way to address the issue using notions from emotional theories, combined with spatiotemporal information and employ online event detection mechanisms to solve it at large scale in a distributed fashion. We present a modular framework that incorporates all of our key ideas and experimentally validate its superiority, in terms of both efficiency and effectiveness, over the state-of-the-art using real life data from the Twitter stream. We also present empirical evidence on the importance of spatiotemporal information in event detection for this setting.

Location is prevalent in most applications nowadays, and is considered a first class citizen in social networks. Locational information is of great significance since it can be used to map information from the online back to the physical world, to contextualize information, or to provide localized recommendations through Location-Based Services (LBS), and can be extended to trajectories and itineraries by adding a time-dimension. Despite all that, location extraction in social networks usually relies on GPS-enabled devices, that provide accurate geodetic coordinates. Nevertheless, most users provide general textual information about their surroundings, such as the city they live in, county or state (or equivalents), without using a GPS-enabled device, which is still valuable information for a number of applications. In this paper, we tackle the problem of extracting location information, usually referred to as geocoding, from additional user-provided content. Instead of using sophisticated and complex algorithms, which are common in online map services but require heavy development and tuning, we rely on software and data which are available online and publically accessible. We discuss the particularities of geocoding in online social networks and present a simple, lightweight, yet efficient approach for location extraction in such a setting. We finally evaluate our approach experimentally on a large corpus of Twitter users.

Acid prehydrolysis with chemical delignification was studied as a method for fractionating lignocellulosic biomass into hemicellulose, lignin and cellulose. Experiments with wheat straw show that hemicellulose can be quantatively separated by prehydrolysis, but the structure of the residue is substantially modified. Delignification of this residue by conventional methods gives significant losses of polysaccharides and a degraded cellulose. The efficiency of the separation can be increased by nonconventional delignification, e.g. chlorination by Cl. In this case, the sugar losses are minimal and further degradation of cellulose during delignification can be avoided, while lignin is quantatively recovered from the pulping liquors.