Papers by Daniela M Romano
Frontiers in psychology, Mar 1, 2024
Introduction: Current research on Autonomous Sensory Meridian Response (ASMR) assumes that ASMR i... more Introduction: Current research on Autonomous Sensory Meridian Response (ASMR) assumes that ASMR is always accompanied by contentment, and it is distinct from frisson due to positive emotions. Thus, research investigations tend to limit their scope to solely focusing on the sensation of relaxation that ASMR induces. This study explores whether it is possible to have a different emotional experience and still perceive ASMR, testing the theory of ASMR as an amplifier of pre-existing emotion instead of a determination of positive affect. The emotional arousal and valence, and mood changes of 180 ASMRcapable and incapable individuals were analysed using questionnaires after altering the affective interpretation associated with auditory ASMR (tapping) with visual priming to examine whether the primed emotion (fearful, relaxing, or neutral) could be amplified. Results: It was found that an ASMR response occurred in all priming conditions, including the fear priming group. No significant difference was found in the emotional outcome or mood of the neutral and relaxing priming groups. Upon comparison with ASMR-incapable individuals, both the relaxing and neutral priming groups demonstrated the same affect, but greater potent for ASMRcapable. Individuals who appraised ASMR after visual fear priming demonstrated a significant decrease in positive emotional valence and increased arousal. The findings suggest that ASMR occurs in both positive and negative emotional situations, suppressing contentment induction if ASMR stimuli are interpreted negatively and amplifying contentment when interpreted positively. While more research is needed, the results highlight that ASMR and frisson might describe the same phenomenon, both a physically felt signature of emotion. Therapeutic usage of ASMR should carefully select appropriate stimuli that emphasise contentment to avoid potential health risks associated with negative emotions until a further understanding of ASMR's affective parameters has been established.
arXiv (Cornell University), Jan 30, 2020
The world of competitive Esports and video gaming has seen and continues to experience steady gro... more The world of competitive Esports and video gaming has seen and continues to experience steady growth in popularity and complexity. Correspondingly, more research on the topic is being published, ranging from social network analyses to the benchmarking of advanced artificial intelligence systems in playing against humans. In this paper, we present ongoing work on an intelligent agent recommendation engine that suggests actions to players in order to maximise success and enjoyment, both in the space of in-game choices, as well as decisions made around play session timing in the broader context. By leveraging temporal data and appropriate models, we show that a learned representation of player psychological momentum, and of tilt, can be used, in combination with player expertise, to achieve state-of-the-art performance in preand post-draft win prediction. Our progress toward fulfilling the potential for deriving optimal recommendations is documented.
We discuss the FearNot! application demonstrator, currently being developed for the EU framework ... more We discuss the FearNot! application demonstrator, currently being developed for the EU framework V project VICTEC. It details the language structure, content, interactions management and design of the FearNot! Demonstrator, as well as presenting the VICTEC project and its motivations. This paper also focuses on the different sets of Speech Act inspired language action lists developed for the project and discusses their use for an interactive language and action system for the elaboration of expressive characters.
A brain-computer interface (BCI) enables users to communicate through a computer using only their... more A brain-computer interface (BCI) enables users to communicate through a computer using only their brain signals, by extracting brain signal features containing information representative of the user's intent, and can be used in a wide variety of areas such as entertainment, rehabilitation, or assistive technologies. In this paper, two novel normalization methods are assessed with the aim of improving the quality of the extracted features: Baseline-Corrected canonical correlation analysis (BC-CCA), and Scaled CCA. Both methods are found to be able to improve classification accuracy in conditions using frequencies with a large range, whilst BC-CCA is the superior of the two, improving SSVEP detection accuracy by as much as 9.22%.
Human Behavior and Emerging Technologies
Pain and discomfort are subjective perceptions that are difficult to quantify. Various methods an... more Pain and discomfort are subjective perceptions that are difficult to quantify. Various methods and scales have been developed to find an optimal manner to describe them; however, these are difficult to use with some categories of patients. Audification of pain has been utilized as feedback in rehabilitation settings to enhance motor perception and motor control, but not in assessment and communication settings. We present a novel tool, the Audification-console for Self-Assessment of Discomfort (ASAD), for assessing and communicating pain and discomfort through sound. The console is a sequence of increasing pitch and frequencies triggered at the press of buttons and displayed as a matrix that can be associated with the subjective perception of pain and discomfort. The ASAD has been evaluated in its ability to capture and communicate discomfort, following a fatigue test in the lower limbs with thirty healthy volunteers, and compared to the most common self-reported methods used in the...
Recommender systems have been used in physical museums to improve visitor experience; yet to asse... more Recommender systems have been used in physical museums to improve visitor experience; yet to assess their impact empirically, researchers often rely on the user experience criteria alone. In this paper, we examine the multidimensionality of visitor experience, specifically the components and factors that shape it. We present a framework that is built on existing bodies of knowledge about visitor experience and that serves as a starting point to further evaluate the transformations caused by the integration of recommender systems in museums. We then conclude that current approaches to testing the impact of recommender systems on visitor experience should be expanded beyond evaluations of user satisfaction level to include the demonstrated aspects of visitor experience. This research aims to contribute to a more in-depth understanding of the differences between visitor and user experience types as well as to address the need for a more comprehensive set of guidelines to evaluate how r...
The 23rd International ACM SIGACCESS Conference on Computers and Accessibility, 2021
We present the iReadMore app, a reading therapy for people with acquired reading or language impa... more We present the iReadMore app, a reading therapy for people with acquired reading or language impairments (known as alexia and aphasia respectively). The app was co-designed by people with alexia and aphasia, and has been demonstrated to significantly improve reading speed and accuracy in a randomized controlled trial. It is intended to be used at home without the support of a therapist. Therefore, accessibility and maintaining therapy engagement are key elements in achieving the high therapy doses required for rehabilitation of reading impairments. As such, these elements were developed in a co-design process that included 50 participants over 2 phases. This demonstration will present the flow of the application and detail how we translated a clinically validated prototype into a publicly available therapy app used by hundreds of people with acquired reading impairments since its release in March 2021.
Heliyon, 2020
We are increasingly exposed to applications that embed some sort of artificial intelligence (AI) ... more We are increasingly exposed to applications that embed some sort of artificial intelligence (AI) algorithm, and there is a general belief that people trust any AI-based product or service without question. This study investigated the effect of personality characteristics (Big Five Inventory (BFI) traits and locus of control (LOC)) on trust behaviour, and the extent to which people trust the advice from an AI-based algorithm, more than humans, in a decision-making card game. Method: One hundred and seventy-one adult volunteers decided whether the final covered card, in a five-card sequence over ten trials, had a higher/lower number than the second-to-last card. They either received no suggestion (control), recommendations from what they were told were previous participants (humans), or an AIbased algorithm (AI). Trust behaviour was measured as response time and concordance (number of participants' responses that were the same as the suggestion), and trust beliefs were measured as self-reported trust ratings. Results: It was found that LOC influences trust concordance and trust ratings, which are correlated. In particular, LOC negatively predicted beyond the BFI dimensions trust concordance. As LOC levels increased, people were less likely to follow suggestions from both humans or AI. Neuroticism negatively predicted trust ratings. Openness predicted reaction time, but only for suggestions from previous participants. However, people chose the AI suggestions more than those from humans, and self-reported that they believed such recommendations more. The results indicate that LOC accounts for a significant variance for trust concordance and trust ratings, predicting beyond BFI traits, and affects the way people select whom they trust whether humans or AI. These findings also support the AI-based algorithm appreciation.
Heliyon, 2020
Introduction: A challenge in defining Internet Gaming Disorder (IGD) is discriminating pathologic... more Introduction: A challenge in defining Internet Gaming Disorder (IGD) is discriminating pathological gameplay from an excessive, yet benign, involvement in video games. Although previous research has explored this theoretical distinction in the context of general computing activities, it merits consideration with regards to online gaming. Additionally, whilst comorbidities of addicted gaming and mental health outcomes have been robustly demonstrated, few studies have examined the role of mediating factors that may contextualise this relationship. As such, the present study aims to validate the distinction between addiction and engagement in online gaming, by considering the mediating roles of coping and social online and offline support in mental health. Method: One hundred and thirty-five participants completed the Computer Engagement/Addiction Questionnaire (CEAS), Depression-Anxiety-Stress Scale (DASS-21), Brief Approach-Avoidance Coping Questionnaire (BACQ) and two versions of the Multidimensional Scale of Perceived Social Support (MSPSS). Results: Correlational analyses showed a clear distinction between gaming addiction and engagement in the context of all of depression, stress and in particular anxiety (DAS) not found in previous studies. Multiple mediation analysis showed a significant mediating effect of coping, (specifically withdrawal/resignation coping) on the relationship between video game addiction and symptoms of DAS. Offline perceived social support was a significant partial mediator in the relationship between gaming addiction and depression, as compared to any kind of online social support. The results support the distinction of the addiction and engagement concepts in gaming. This study may inform future clinical classifications of IGD, with implications on how pathological gaming is treated.
2017 8th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), Sep 1, 2017
A brain-computer interface (BCI) enables users to communicate through a computer using only their... more A brain-computer interface (BCI) enables users to communicate through a computer using only their brain signals, by extracting brain signal features containing information representative of the user's intent, and can be used in a wide variety of areas such as entertainment, rehabilitation, or assistive technologies. In this paper, two novel normalization methods are assessed with the aim of improving the quality of the extracted features: Baseline-Corrected canonical correlation analysis (BC-CCA), and Scaled CCA. Both methods are found to be able to improve classification accuracy in conditions using frequencies with a large range, whilst BC-CCA is the superior of the two, improving SSVEP detection accuracy by as much as 9.22%.
Agent-Based Simulation of Organizational Behavior, 2016
This chapter stresses the need for research in organizations to reflect the coevolutionary and co... more This chapter stresses the need for research in organizations to reflect the coevolutionary and complex nature of the changing world we live in today. We argue that key concepts can be abstracted from biological evolution, and used as a starting point for the conceptual development of such approaches. In addition, computational modeling techniques can be used not only as a tool for shaping this conceptual development, but simulating changing behaviors at multiple levels in real organizations. While a number of researchers have developed co-evolutionary accounts of organizational change, these efforts have been constrained by an entity interpretation of the unit of co-evolution. In this latter view, it is assumed that organizations act as vehicles for bundles of routines, being subject to external selection forces only. As a result change occurs largely through the actions of customers or senior executives. We argue that practice-based interpretations offer an alternative approach in the modeling of co-evolution, unpacking the complexity and interconnected agency within and beyond organizations. Building on these conceptual foundations, we outline key conceptual, empirical and ethical challenges in developing related computational models. We argue that such simulation models can be used by managers to help them navigate complex future worlds.
USES Conference Proceedings, 2015
In complex environment accurate decision making requires making sense of complex and often large ... more In complex environment accurate decision making requires making sense of complex and often large sets of data. Support is needed to model, understand and make predictions. Virtual environments can provide an ideal platform for presenting complex information and intelligent agents can support prediction and decision making.
Proceedings of the 4th international conference on Collaborative virtual environments, 2002
Commercial organisations that are in dispute will sometimes seek to settle their differences with... more Commercial organisations that are in dispute will sometimes seek to settle their differences without resorting to legal proceedings through a process of structured and facilitated negotiation called Alternate Dispute Resolution (ADR). Traditionally ADR negotiations are conducted by co-locating the mediator, witnesses, supporting evidence and representatives of each party. This paper describes a novel experiment that has been conducted at the University of Leeds to investigate whether an augmented collaborative environment could provide a realistic alternative to co-locating individuals for ADR negotiations. The individuals that took part in the experiment included an experienced mediator and practising legal representatives. The augmented collaborative environment was based on a video conferencing system that was enhanced to enable virtual artefacts representing items of evidence to be blended directly into the video streams. This experiment sits within the framework of the Court 21 Project, that is seeking to identify how new technology can be used to improve the different aspects of the legal system [10].
International Journal of Gaming and Computer-Mediated Simulations, 2010
Affective bio-feedback can be an important instrument to enhance the game experience. Several stu... more Affective bio-feedback can be an important instrument to enhance the game experience. Several studies have provided evidence of the usefulness of physiological signals for affective gaming; however, due to the limited knowledge about the distinctive autonomic signatures for every emotion, the pattern matching models employed are limited in the number of emotions they are able to classify. This paper presents a bio-affective gaming interface (BAGI) that can be used to customize a game experience according to the player’s emotional response. Its architecture offers important characteristics for gaming that are important because they make possible the reusability of previous findings and the inclusion of new models to the system. In order to prove the effectiveness of BAGI, two different types of neural networks have been trained to recognize emotions. They were incorporated into the system to customize, in real-time, the computer wallpaper according to the emotion experienced by the u...
Sustainable integrated catchment management is a complex task that often involves finding comprom... more Sustainable integrated catchment management is a complex task that often involves finding compromise between the views of multiple stakeholders that may not easily be brought to consensus. Interactive three dimensional (3D) visualisations of landscapes can facilitate discussion, but these can only partially inform decision makers as many important aspects of interventions are abstract. Such abstract criteria however can be modelled using a Bayesian Network (BN), combining expert opinions, empirical evidence and data derived from existing models. Thus, it is hypothesised that by combining an interactive 3D landscape design software with a BN, a decision support tool is created that brings together the complementary strengths of both techniques. To test this idea, such a tool has been developed for a river management problem in Sheffield, UK. Impounding the River Don that flows through the city are many weirs which form significant landmarks of the urban riverscape and determine the recreational quality for canoeists. Consequently, management decisions must account for the effect of weir modification not only on the visual aesthetic, but also on the abstract recreational quality of the river for canoeists. To support this problem, an interactive tool has been developed that integrates 3D design and visualisation of weir modification options with indicators of the utility of the river from the perspective of the canoeists, modelled using a BN. It is demonstrated that it is possible to feed back the indicator assessment of a design alongside the visualisation or as part the visualisation.
Frontiers in Psychology, Jul 5, 2023
Introduction: Aggressive behaviour is a challenge for society. There continues to be considerable... more Introduction: Aggressive behaviour is a challenge for society. There continues to be considerable debate over whether the consumption of violent video games affects aggression, as violent video game content has become more accessible in recent years due to the growing use of online distribution platforms. Personality traits often linked to aggression, such as narcissism and self-esteem, have been considered in the context of violent video game play and their relationship with aggression. Methods: We surveyed an international population of 166 game players on their personality traits and their three favourite video game choices, which were classified as violent or non-violent, using Pan European Game Information (PEGI) 16 and 18 ratings. Results: We found that violent video game choice is a predictor of verbal aggression alongside narcissism, and hostility alongside self-esteem. A categorical regression highlighted the desire to impersonate society's undesirable role models (e.g., 'be a thief or a killer') as one of the motivations for aggression and violent video game choice. Discussion: These findings show that video game violence should be considered a risk factor for aggression, as in other violent media, as it provides a social reinforcement of aggressive behaviour and observational learning of aggressive models, calling for the introduction of stricter online age verification procedures on online game platforms to safeguard children from violent video game content; and increased use of parental controls on content fruition. More granularity should be considered in the PEGI classifications.
Between 2002 and 2012 the number of pilgrims taking part in the 5-day hajj (the annual pilgrimage... more Between 2002 and 2012 the number of pilgrims taking part in the 5-day hajj (the annual pilgrimage to Mecca) rose dramatically from 1.9m to 3.2m, before stabilizing at around 2 million following the introduction of new quotas in 2013. The gathering together of so many people has obvious crowd-safety implications, ranging from stampedes and protests to pickpocketing and dis- ease control, and there is an obvious need for models and simulations of the relevant crowd behaviours. More- over, the regular occurrence of the event, the size and diversity of the crowds involved, and the amount of freely available information make this an excellent case study for the study of crowd behaviour. We survey recent at- tempts to model the key hajj rituals of tawaf (during which pilgrims collectively circumambulate the Ka’aba seven times) and sa’yee (running or walking seven times between two nearby hills), and highlight ways in which some of the limitations of these studies may be overcome in future...
2019 4th Technology Innovation Management and Engineering Science International Conference (TIMES-iCON), 2019
Credit as a part of our consumptive life has helped a lot of people. As a financial product, it i... more Credit as a part of our consumptive life has helped a lot of people. As a financial product, it is used widely along with the growth of economic and financial services. Therefore, credit is very risky so that motivating the financial institution to use a system called credit scoring to make a decision about acceptance. However, the conventional credit scores is calculated from the user's financial history in financial institution. This method causes people without any financial history or account, such as students, being unnoticed by the system, then their credit proposal is declined. This phenomenon insists the researchers thinking about a new credit scoring system that facilitates people from different economic background. Knowing that people nowadays will spend any money and time on their smartphone, we make a hypothesis about how smartphone usage behavior can be the answer. Then, the survey is conducted to 90 respondents from low to high economic background to model their credit limit. This paper shows that smartphone usage has some insights that can be computed through Multi-Cluster Feature Selection (MCFS). The selected features are Brand of phone, Frequency of changing the phone, Occupation, Data usage for game, Cost for phone, Data usage for social media, Reason of changing the phone, Money for data, Protect personal interest, Age, Spend last money, and Pay for you.
Recently technologies have improved training practices tremendously, especially practices that re... more Recently technologies have improved training practices tremendously, especially practices that require visualization and collaboration to enhance the understanding of any situation and to deploy strategies to solve these problems. Visualization of problems enhanc es a trainee’s understanding of it in a more natural way that mimics everyday practice in the real world. Once a me ntal picture of the situation has been constructed, the train ee can then try different approaches to remedy it and there for learn by experience. This paper investigates the use of collaborative virtual environment (CVE) technology fo r training purposes. We present an architecture for CVEs developed with the purpose of being domain independent by separating scenario logic from the simulation environment. We believe that such separation leads to a flexible environment that can easily be modified into ew scenarios. To demonstrate this we have built two scen arios to show how the logic can be separated and cont...
Uploads
Papers by Daniela M Romano