0000000001037694
AUTHOR
Mehdi Ben Lazreg
The Diffusion of Crisis-Related Communication on Social Media: An Empirical Analysis of Facebook Reactions
During a crisis, authorities need to effectively disseminate information. We address the problem of deciding how crisis-related information should be published on Facebook to reach as many people as possible. We examine three recent terrorist attacks in Berlin, London and Stockholm. Our specific focus lies with official Facebook pages by municipalities and emergency service agencies. We collected posts about the events, along with the number of shares, likes and emotional reactions to them. In a regression analysis, several variables were examined that capture decisions on which information to publish and how. Posts containing condolences were found to result in three times as many emotiona…
A Churn prediction model based on gaussian processes
Masteroppgave i industriell økonomi og teknologiledelse IND590 2013 – Universitetet i Agder, Grimstad The telecommunication’s market has changed to a saturated one during the past few years. This makes it relatively costly to acquire new customers than to retain existing ones. Recent research has further showed that identifying potential customers who intend to leave a service provider for another (churners) and offering them an incentive to keep their subscriptions can produce significant savings for the telecommunication company. However, in most cases, it turned out that most of the used techniques to solve this problem fails to address the complex relationship between customer features …
An Iterative Information Retrieval Approach from Social Media in Crisis Situations
During to past few years, social media have gained a pivotal role in crisis communication. Its usage has ranged from informing the public about the status of a crisis and what precaution need to be taken, to family members checking on the safety of loved ones. Despite the widespread use of social media in crises situations and the clear potential benefit from collecting potential critical information from social media, emergency management services (EMSs) are still reluctant to use social media as a source of information to improve their situational awareness. One of the reasons for the reluctance is that crises management are typically overloaded with information. Adding social media will …
A Neural Turing~Machine for Conditional Transition Graph Modeling
Graphs are an essential part of many machine learning problems such as analysis of parse trees, social networks, knowledge graphs, transportation systems, and molecular structures. Applying machine learning in these areas typically involves learning the graph structure and the relationship between the nodes of the graph. However, learning the graph structure is often complex, particularly when the graph is cyclic, and the transitions from one node to another are conditioned such as graphs used to represent a finite state machine. To solve this problem, we propose to extend the memory based Neural Turing Machine (NTM) with two novel additions. We allow for transitions between nodes to be inf…
Vector representation of non-standard spellings using dynamic time warping and a denoising autoencoder
The presence of non-standard spellings in Twitter causes challenges for many natural language processing tasks. Traditional approaches mainly regard the problem as a translation, spell checking, or speech recognition problem. This paper proposes a method that represents the stochastic relationship between words and their non-standard versions in real vectors. The method uses dynamic time warping to preprocess the non-standard spellings and autoencoder to derive the vector representation. The derived vectors encode word patterns and the Euclidean distance between the vectors represents a distance in the word space that challenges the prevailing edit distance. After training the autoencoder o…
A Bayesian Network Model for Fire Assessment and Prediction
Smartphones and other wearable computers with modern sensor technologies are becoming more advanced and widespread. This paper proposes exploiting those devices to help the firefighting operation. It introduces a Bayesian network model that infers the state of the fire and predicts its future development based on smartphone sensor data gathered within the fire area. The model provides a prediction accuracy of 84.79i¾?% and an area under the curve of 0.83. This solution had also been tested in the context of a fire drill and proved to help firefighters assess the fire situation and speed up their work.
Information Abstraction from Crises Related Tweets Using Recurrent Neural Network
Social media has become an important open communication medium during crises. The information shared about a crisis in social media is massive, complex, informal and heterogeneous, which makes extracting useful information a difficult task. This paper presents a first step towards an approach for information extraction from large Twitter data. In brief, we propose a Recurrent Neural Network based model for text generation able to produce a unique text capturing the general consensus of a large collection of twitter messages. The generated text is able to capture information about different crises from tens of thousand of tweets summarized only in a 2000 characters text.
Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities
Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is to define a metric over a word space that quantifies and sums up the differences between characters in two strings. The state-of-the-art in the area has, surprisingly, not evolved much during the last few decades. The majority of the metrics are based on a simple comparison between character and character distributions without consideration for the context of the words. This paper proposes a string metric that encompasses similarities between strings bas…
Combining a context aware neural network with a denoising autoencoder for measuring string similarities
Abstract Measuring similarities between strings is central for many established and fast-growing research areas, including information retrieval, biology, and natural-language processing. The traditional approach to string similarity measurements is to define a metric with respect to a word space that quantifies and sums up the differences between characters in two strings; surprisingly, these metrics have not evolved a great deal over the past few decades. Indeed, the majority of them are still based on making a simple comparison between character and character distributions without considering the words context. This paper proposes a string metric that encompasses similarities between str…
Fire simulation-based adaptation of SmartRescue App for serious game: Design, setup and user experience
Managing the crisis by embracing game and simulation elements and human participation into an interactive system is a mean to learn about responding to unexpected events. This so-called serious game approach is adopted in a summer school for crisis management attended by doctoral students and practitioners, as a part of its learning curriculum. The participants took part in the Disaster in my Backyard serious game, designed as a realistic crisis environment. A smartphone app encompassing fire simulations of a five-story apartment, showing how the flame, smoke and temperature of the fire developed over time from floor to floor, was tested in this serious game scenario. The color-coding of sm…
Not a Target. A Deep Learning Approach for a Warning and Decision Support System to Improve Safety and Security of Humanitarian Aid Workers
Humanitarian aid workers who try to provide aid to the most vulnerable populations in the Middle East or Africa are risking their own lives and safety to help others. The current lack of a collaborative real-time information system to predict threats prevents responders and local partners from developing a shared understanding of potentially threatening situations, causing increased response times and leading to inadequate protection. To solve this problem, this paper presents a threat detection and decision support system that combines knowledge and information from a network of responders with automated and modular threat detection. The system consists of three parts. It first collects te…