Web bots are vital for the web as they can be used to automate several actions, some of which would have otherwise been impossible or very time consuming. These actions can be benign, such as website testing and web indexing, or malicious, such as unauthorised content scraping, scalping, vulnerability scanning, and more. To detect malicious web bots, recent approaches examine the visitors’ fingerprint and behaviour. For the latter, several values (i.e., features) are usually extracted from visitors’ web logs and used as input to train machine learning models. In this research we show that web bots can use recent advances in machine learning, and, more specifically, Reinforcement Learning (RL), to effectively evade behaviour-based detection techniques. To evaluate these evasive bots, we examine (i) how well they can evade a pre-trained bot detection framework, (ii) how well they can still evade detection after the detection framework is re-trained on new behaviours generated from the evasive web bots, and (iii) how bots perform if re-trained again on the re-trained detection framework. We show that web bots can repeatedly evade detection and adapt to the re-trained detection framework to showcase the importance of considering such types of bots when designing web bot detection frameworks.

High-quality and emotionally validated material is a necessary basis for well-designed experiments in affective cognition and neuroscience research. Videos of existing databases are recorded using and viewed on devices that were current at the time of the design. With the continuous transition to more recent, higher-resolution devices, new databases are needed, and older ones need to be regularly updated. This is particularly true for virtual reality (VR) head-mounted displays (HMD) which, due to the proximity of the eyes to the screen, are extremely prone to low-resolution effects, resulting in unclear images. However, current databases typically feature high intra-variability, combining videos of varied length and quality, which can be problematic when looking at time domain features and physiological signals. In our study, 60 online videos, 30 seconds long were rated by 86 participants in an online survey using a novel class of affective sliders. Mean arousal and valence ratings were calculated for all videos and used for video classification into positive, neutral, and negative categories identified through cluster analysis. Mean ratings showed a parabolic, u-shape curve of arousal and valence present in other similar studies. Two-step clustering has successfully identified 3 clusters we selected and placed 88.3% of videos in the cluster we predicted. Our results suggest that online questionnaires could provide an easier way to update video databases with similar effectiveness as lab-based experiments. Videos and rating table are available for download at: https://gnacek.com/affective-video-database-online-study

Drug recommendation is denoted as the task of predicting drug combinations for patients' therapies with complex diseases (i.e., thrombosis, diabetes, etc.). These patients usually suffer from polypharmacy, and consequently various drug drug interactions. In this paper, we integrate the patients' Electronic Health Records (EHRs) with an adversarial Drug-Drug Interaction (DDI) knowledge graph to predict the next drug combination for a patient's therapy and minimize the drug side effects. In particular, we integrate an EHR graph, which incorporates the patient, the disease, the therapy, and the drug information, with an Adversarial DDI knowledge graph to recommend both accurate and safe medication. We also predict mortality and the time to death of critically-ill patients, to identify clinically meaningful predictors (e.g., harmful drug combinations). By identifying those drugs which can act adversarially, we are able to improve either the efficacy of the patient's therapy or minimize the toxicity and drug side effects. We have run experiments with a real-life medical data set. Our results show that we can assist doctors to prescribe effective and safe medication for the patients' treatment.

The term “aesthetic experience” corresponds to the inner state of a person exposed to the form and content of artistic objects. Quantifying and interpreting the aesthetic experience of people in different contexts can contribute towards (a) creating context and (b) better understanding people’s affective reactions to different aesthetic stimuli. Focusing on different types of artistic content, such as movies, music, literature, urban art, ancient artwork, and modern interactive technology, the goal of this workshop is to enhance the interdisciplinary collaboration among researchers coming from the following domains: affective computing, aesthetics, human-robot/computer interaction, digital archaeology and art, culture, addictive games.

The term “aesthetic experience” corresponds to inner states of individuals exposed to art. Investigating form, content, and aesthetic values of artistic objects, indoor and outdoor spaces, urban areas, and modern interactive technology is essential to improve social behaviour, quality of life, and health of humans in the long term. Quantifying and interpreting the aesthetic experience of art receivers in different contexts can contribute towards (a) creating art and (b) better understanding humans’ affective reactions to aesthetic stimuli. Focusing on different types of artistic content, such as movies, music, urban art, ancient artwork, and modern interactive technology, the goal of the Second International Workshop on Multimodal Affect and Aesthetic Experience is to enhance the interdisciplinary collaboration among researchers from the following domains: affective computing, aesthetics, human-robot interaction, and digital archaeology and art.

Recognizing emotional reactions of movie audiences to affective movie content is a challenging task in affective computing. Previous research on induced emotion recognition has mainly focused on using audio-visual movie content. Nevertheless, the relationship between the perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audiences (induced emotions) is unexplored. In this work, we studied the relationship between perceived and induced emotions of movie audiences. Moreover, we investigated multimodal modelling approaches to predict movie induced emotions from movie content based features, as well as physiological and behavioral reactions of movie audiences. To carry out analysis of induced and perceived emotions, we first extended an existing database for movie affect analysis by annotating perceived emotions in a crowd-sourced manner. We find that perceived and induced emotions are not always consistent with each other. In addition, we show that perceived emotions, movie dialogues, and aesthetic highlights are discriminative for movie induced emotion recognition besides spectators' physiological and behavioral reactions. Also, our experiments revealed that induced emotion recognition could benefit from including temporal information and performing multimodal fusion. Moreover, our work deeply investigated the gap between affective content analysis and induced emotion recognition by gaining insight into the relationships between aesthetic highlights, induced emotions, and perceived emotions.

Venous thromboembolism (VTE) is the third most common cardiovascular condition. Some high risk patients diagnosed with VTE need immediate treatment and monitoring in intensive care units (ICU) as the mortality rate is high. Most of the published predictive models for ICU mortality give information on in-hospital mortality using data recorded in the first day of ICU admission. The purpose of the current study is to predict in-hospital and after-discharge mortality in patients with VTE admitted to ICU using a machine learning (ML) framework. We studied 2,468 patients from the Medical Information Mart for Intensive Care (MIMIC-III) database, admitted to ICU with a diagnosis of VTE. We formed ML classification tasks for early and late mortality prediction. In total, 1,471 features were extracted for each patient, grouped in seven categories each representing a different type of medical assessment. We used an automated ML platform, JADBIO, as well as a class balancing combined with a Random Forest classifier, in order to evaluate the importance of class imbalance. Both methods showed significant ability in prediction of early mortality (AUC =0.92). Nevertheless, the task of predicting late mortality was less efficient (AUC =0.82). To the best of our knowledge, this is the first study in which ML is used to predict short-term and long-term mortality for ICU patients with VTE based on a multitude of clinical features collected over time.

The term 'aesthetic experience' corresponds to the inner state of a person exposed to form and content of artistic objects. Exploring certain aesthetic values of artistic objects, as well as interpreting the aesthetic experience of people when exposed to art can contribute towards understanding (a) art and (b) people's affective reactions to artwork. Focusing on different types of artistic content, such as movies, music, urban art and other artwork, the goal of this workshop is to enhance the interdisciplinary collaboration between affective computing and aesthetics researchers.

Automated programs (bots) are responsible for a large percentage of website traffic. These bots can either be used for benign purposes, such as Web indexing, Website monitoring (validation of hyperlinks and HTML code), feed fetching Web content and data extraction for commercial use or for malicious ones, including, but not limited to, content scraping, vulnerability scanning, account takeover, distributed denial of service attacks, marketing fraud, carding and spam. To ensure their security, Web servers try to identify bot sessions and apply special rules to them, such as throttling their requests or delivering different content. The methods currently used for the identification of bots are based either purely on rule-based bot detection techniques or a combination of rule-based and machine learning techniques. While current research has developed highly adequate methods for Web bot detection, these methods' adequacy when faced with Web bots that try to remain undetected hasn't been studied. For this reason, we created and evaluated a Web bot detection framework on its ability to detect conspicuous bots separately from its ability to detect advanced Web bots. We assessed the proposed framework performance using real HTTP traffic from a public Web server. Our experimental results show that the proposed framework has significant ability to detect Web bots that do not try to hide their bot identity using HTTP Web logs (balanced accuracy in a false-positive intolerant server > 95%). However, detecting advanced Web bots that present a browser fingerprint and may present a humanlike behaviour as well is considerably more difficult.

Reflecting upon the sustainability challenges cities will be facing in the near future and the recent technological developments allowing cities to become "smart", we introduce IDEAL-CITIES; a framework aiming to provide an architecture for cyber-physical systems to deliver a data-driven Circular Economy model in a city context. In the IDEAL-CITIES ecosystem, the city's finite resources as well as citizens will form the pool of intelligent assets in order to contribute to high utilization through crowdsourcing and real-time decision making and planning. We describe two use cases as a vehicle to demonstrate how a smart city can serve the Circular Economy paradigm.

Online gambling, unlike other mediums of problem-atic and addictive behaviours, such as tobacco and alcohol, offers unprecedented opportunities for building information systems that are able to monitor and understand a user's behaviour in real-time and adapt persuasive messages and interactions that would fit their personal profile and usage context. Online gambling industry usually provides Application Programming Interfaces (APIs) meant mainly to enable third-party applications to network with their gambling services and enhance a user's gambling experience. In this industrial practice and experience paper, we advocate that such API's can also be used to retrieve gamblers' online data, such as browsing and betting history, promotions and available offers and use it to build more intel-ligent and proactive responsible gambling information systems. We report on our industrial experience in this field and make the argument that data available for persuasive marketing and usability should, under specific usage conditions, also be made available for responsible gambling information systems. This principle would provide equal opportunities for both directions. We discuss the psychological foundations of our proposed solution and the risks and challenges typically found when building such a software-assisted intervention, persuasion and emotion regulation technology. We also shed light on its potential implications from the perspectives of social corporate responsibility and data protection. We finally propose a conceptual architecture to demonstrate our vision and explain how it can be implemented. In the wider context, the paper is meant to provide insights on building behavioural awareness and regulation information systems in relation to problematic digital media usage.

Detection of aesthetic highlights is a challenge for understanding the affective processes taking place during movie watching. In this article, we study spectators’ responses to movie aesthetic stimuli in a social context. Moreover, we look for uncovering the emotional component of aesthetic highlights in movies. Our assumption is that synchronized spectators’ physiological and behavioral reactions occur during these highlights because: ( i ) aesthetic choices of filmmakers are made to elicit specific emotional reactions (e.g., special effects, empathy, and compassion toward a character) and ( ii ) watching a movie together causes spectators’ affective reactions to be synchronized through emotional contagion. We compare different approaches to estimation of synchronization among multiple spectators’ signals, such as pairwise, group, and overall synchronization measures to detect aesthetic highlights in movies. The results show that the unsupervised architecture relying on synchronization measures is able to capture different properties of spectators’ synchronization and detect aesthetic highlights based on both spectators’ electrodermal and acceleration signals. We discover that pairwise synchronization measures perform the most accurately independently of the category of the highlights and movie genres. Moreover, we observe that electrodermal signals have more discriminative power than acceleration signals for highlight detection.

Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

Detection of emotional and aesthetic highlights is a challenge for the affective understanding of movies. Our assumption is that synchronized spectators' physiological and behavioral reactions occur during these highlights. We propose to employ the periodicity score to capture synchronization among groups of spectators' signals. To uncover the periodicity score's capabilities, we compare it with baseline synchronization measures, such as the nonlinear interdependence and the windowed mutual information. The results show that the periodicity score and the pairwise synchronization measures are able to capture different properties of spectators' synchronization, and they indicate the presence of some types of emotional and aesthetic highlights in a movie based on spectators' electro-dermal and acceleration signals.

Detection of highlights in movies is a challenge for the affective understanding and implicit tagging of films. Under the hypothesis that synchronization of the reaction of spectators indicates such highlights, we define a synchronization measure between spectators that is capable of extracting movie highlights. The intuitive idea of our approach is to define (a) a parameterization of one spectator's physiological data on a manifold; (b) the synchronization measure between spectators as the Kolmogorov-Smirnov distance between local shape distributions of the underlying manifolds. We evaluate our approach using data collected in an experiment where the electro-dermal activity of spectators was recorded during the entire projection of a movie in a cinema. We compare our methodology with baseline synchronization measures, such as correlation, Spearman's rank correlation, mutual information, Kolmogorov-Smirnov distance. Results indicate that the proposed approach allows to accurately distinguish highlight from non-highlight scenes.

In the present work we evaluate a detector of negative emotional states (DNES) that serves the purpose of enhancing a spoken dialogue system, which operates in smart-home environment. The DNES component is based on Gaussian mixture models (GMMs) and a set of commonly used speech features. In comprehensive performance evaluation we utilized a well-known acted speech database and real-world speech recordings. The real-world speech was collected during interaction of naive users with our smart-home spoken dialogue system. The experimental results show that the accuracy of recognizing negative emotions on the real- world data is lower than the one reported when testing on the acted speech database, though much promising, considering that, often, humans are unable to distinguish the emotion of other humans judging only from speech.

Graph classification is an important data mining task that has attracted considerable attention recently. This paper presents a probabilistic substructure-based approach for classifying graph-based data. More specifically, we use a frequent subgraph mining algorithm to extract substructure based descriptors and apply the maximum entropy principle to build a classification model from the frequent subgraphs. We perform extensive experiments to compare the performance of the proposed approach against existing feature vector methods using AdaBoost and support vector machine.