35 research outputs found
Using psycholinguistic features for profiling first language of authors
No full textThis study empirically evaluates the effectiveness of different feature types for the classification of the first language of an author. In particular, it examines the utility of psycholinguistic features, extracted by the Linguistic Inquiry and Word Count (LIWC) tool, that have not previously been applied to the task of author profiling. As LIWC is a tool that has been developed in the psycholinguistic field rather than the computational linguistics field, it was hypothesized that it would be effective, both as a single type feature set because of its psycholinguistic basis, and in combination with other feature sets, because it should be sufficiently different to add insight rather than redundancy. It was found that LIWC features were competitive with previously used feature types in identifying the first language of an author, and that combined feature sets including LIWC features consistently showed better accuracy rates and average F measures than were achieved by the same feature sets without the LIWC features. As a secondary issue, this study also examined how effectively first language classification scaled up to a larger number of possible languages. It was found that the classification scheme scaled up effectively to the entire 16 language collection from the International Corpus of Learner English, when compared with results achieved on just 5 languages in previous research. 2012 ASIS&T
Participant observation of griefing in a journey through the World of Warcraft
No full textThrough the ethnographic method of participant observation in World of Warcraft, this paper aims to document various actions that may be considered griefing among the Massively Multiplayer Online Role-Playing Game community. Griefing as a term can be very subjective, so witnessing the anti-social and intentional actions first-hand can be used as a means to understand this subjectivity among players as well as produce a thorough recount of some of the toxic behavior in this genre. The participant observation was conducted across several years and expansions of World of Warcraft and the author became familiar with many griefing related actions; although some of these were perceived as acceptable game-play elements
Position : intent-aligned ai systems must optimize for agency preservation
No full textA central approach to AI-safety research has been to generate aligned AI systems: i.e. systems that do not deceive users and yield actions or recommendations that humans might judge as consistent with their intentions and goals. Here we argue that truthful AIs aligned solely to human intent are insufficient and that preservation of long-term agency of humans may be a more robust standard that may need to be separated and explicitly optimized for. We discuss the science of intent and control and how human intent can be manipulated and we provide a formal definition of agency-preserving AI-human interactions focusing on forward-looking explicit agency evaluations. Our work points to a novel pathway for human harm in AI-human interactions and proposes solutions to this challenge. Copyright 2024 by the author(s
Assessing the impact of griefing in MMORPGs using self-determination theory
No full textToxic behavior has been impacting players in online multiplayer environments since their inception. Griefing is a type of toxic behavior that focuses on player-to-player in-game disruption and is quite prevalent. However, research into the extent of the impact is still scarce. The present study investigated the impact on the psychological needs of autonomy, competence, and relatedness, as defined by the self-determination theory, for players that perform griefing (the griefers) and those subjected to griefing (the griefed). A sample of 656 respondents from massively multiplayer online role-playing game communities participated in the study. The results discovered that for the majority of players there is no change to their wellbeing, but that when there was a change, the griefed players in general were impacted more negatively, and the perpetrators were impacted more positively. Significant associations also revealed that the magnitude of impacts increased as the player was subjected to or performed griefing more frequently. © 2024 The Author
Project Triton : A study into delivering targeted information to an individual based on implicit and explicit data.
No full textThe World Wide Web is frequently seen as a source of knowledge, however much of this remains undiscovered by its users. In recent times, recommender systems (e.g. Digg and Last.fm) have attempted to bridge this gap, alerting users to previously untapped knowledge. As more socially oriented services appear on the Web (e.g. Facebook and MySpace), it has never been easier to obtain information pertaining to an individual’s interests. At present, solutions for automated data recommendation tend to be highly topic specific (recommending only a certain topic such as news) and often only allow access to the system using monolithic interfaces. This report hopes to detail the stages from research to evaluation involved in creating an extensible framework, which will operate without the need for human intervention. The framework will feature several proof-of-concept plugins residing in a custom workflow, which target information that is useful to the user. Information will be retrieved automatically through plugins involved with data gathering (such as feed processing and page scraping), while users’ interests will be obtained implicitly (for example, using header information to derive location) or explicitly (taking advantage of Social Network APIs such as Facebook Connect). Finally, Third Parties will be able to integrate the framework into their own solutions using the customisable XML API (written in PHP), so that their products can provide custom user interfaces without style constraints
Explainable robotic systems: understanding goal-driven actions in a reinforcement learning scenario
No full textRobotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot’s actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent’s observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson’s correlation and the mean squared error. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature
Explainable reinforcement learning for broad-XAI: a conceptual framework and survey
No full textBroad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent’s behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) aims to develop techniques to extract concepts from the agent’s: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. CXF is designed to incorporate many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes its decisions. This paper aims to: establish XRL as a distinct branch of XAI; introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper discusses how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI. © 2023, The Author(s)
Empirical evaluation methods for multiobjective reinforcement learning algorithms
No full textWhile a number of algorithms for multiobjective reinforcement learning have been proposed, and a small number of applications developed, there has been very little rigorous empirical evaluation of the performance and limitations of these algorithms. This paper proposes standard methods for such empirical evaluation, to act as a foundation for future comparative studies. Two classes of multiobjective reinforcement learning algorithms are identified, and appropriate evaluation metrics and methodologies are proposed for each class. A suite of benchmark problems with known Pareto fronts is described, and future extensions and implementations of this benchmark suite are discussed. The utility of the proposed evaluation methods are demonstrated via an empirical comparison of two example learning algorithms. © 2010 The Author(s)
The impact of environmental stochasticity on value-based multiobjective reinforcement learning
No full textA common approach to address multiobjective problems using reinforcement learning methods is to extend model-free, value-based algorithms such as Q-learning to use a vector of Q-values in combination with an appropriate action selection mechanism that is often based on scalarisation. Most prior empirical evaluation of these approaches has focused on deterministic environments. This study examines the impact on stochasticity in rewards and state transitions on the behaviour of multi-objective Q-learning. It shows that the nature of the optimal solution depends on these environmental characteristics, and also on whether we desire to maximise the Expected Scalarised Return (ESR) or the Scalarised Expected Return (SER). We also identify a novel aim which may arise in some applications of maximising SER subject to satisfying constraints on the variation in return and show that this may require different solutions than ESR or conventional SER. The analysis of the interaction between environmental stochasticity and multi-objective Q-learning is supported by empirical evaluations on several simple multiobjective Markov Decision Processes with varying characteristics. This includes a demonstration of a novel approach to learning deterministic SER-optimal policies for environments with stochastic rewards. In addition, we report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions. Having highlighted the limitations of value-based model-free MORL methods, we discuss several alternative methods that may be more suitable for maximising SER in MOMDPs with stochastic transitions. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature
