This paper explores the applicability of Convergent Cross Mapping (CCM) and its extension, Time Delay Convergent Cross Mapping (TDCCM), to assess the causal relationships between Bitcoin, the S&P 500 index, and gold. Unlike conventional causality analysis methods, such as Granger causality or transfer entropy, CCM accounts for non-separable, weakly connected dynamic systems, and TDCCM explicitly incorporates time lags during cross-mapping, enabling the detection of complex causal relationships in systems with shared nonlinear behavior. This makes it particularly suitable for financial time series that often exhibit chaotic and nonlinear dynamics, particularly during periods of market instability. We integrate TDCCM with simplex projection and sequential locally weighted global linear map (S-map) algorithms, applying a sliding window approach to identify short time intervals characterized by high levels of nonlinearity and chaoticity. Using this approach, we uncovered a strong causal relationship between Bitcoin and the S&P 500 index during the onset of the COVID-19 pandemic. Our analysis reveals a bidirectional causal relationship between Bitcoin and the S&P 500 index, highlighting their interconnectedness during periods of heightened economic uncertainty. Furthermore, we find a unidirectional causal influence of Bitcoin on gold, reflecting Bitcoin’s evolving role as a macroeconomic indicator and its growing relevance as an alternative store of value. These findings provide insight into the dynamics between cryptocurrencies and traditional financial markets, particularly during periods of global economic disruption. • We use Time Delay Convergent Cross Mapping (TD-CCM) to identify and quantify lagged causal interactions between financial time series (Bitcoin, Gold, and the S&P 500 index), which is a more recent and less explored method for Time Series causality. • We report a comprehensive and replicable methodology to apply TD-CCM to non-linear TS, based on combining the S-Map and Prediction Decay algorithm with a sliding window technique, while validating with surrogate analysis. • We show evidence of strong causal influence from Bitcoin to Gold and bidirectional causality between Bitcoin and the S&P 500 Index during significant economic events like the COVID-19 pandemic.

In the recent advancements in application of deep learning to time series forecasting, focus has shifted from training transformers end-to-end to efficiently leveraging the predictive capabilities of Large Language Models (LLMs). Models that encode the time series data to interact with a frozen LLM backbone have been shown to outperform transformers on all benchmark datasets. However, their efficiency on complex datasets, which do not show clear seasonality or trend, remains an open question. In this work, we seek to evaluate the performance of reprogrammed LLMs on the Bitcoin price chart, a financial time series known for its complexity and high volatility. We propose effective methods to improve the performance of Time-LLM, a State-of-the-art (SOTA) method, on such a time series. First, we propose structural improvements to Time-LLM. Second, we suggest an efficient way to handle the non-stationarity of the dataset. Finally, we propose an efficient method for passing additional financial information to the LLM. Our results demonstrate a 50% improvement on the average percentage loss and a 5% increase on accuracy of our adapted Time-LLM architecture on Bitcoin data when compared to SOTA models, including the original Time-LLM model. This highlights the impact on forecast accuracy of domain-specific decision making in data processing and feature selection.

Data from different modalities, such as infrared and visible images, can offer complementary information, and integrating such information can significantly enhance the capabilities of a system to perceive and recognize its surroundings. Thus, multi-modal object detection has widespread applications, particularly in challenging weather conditions like low-light scenarios. The core of multi-modal fusion lies in developing a reasonable fusion strategy, which can fully exploit the complementary features of different modalities while preventing a significant increase in model complexity. To this end, this paper proposes a novel lightweight cross-fusion module named Channel-Patch Cross Fusion (CPCF), which leverages Channel-wise Cross-Attention (CCA), Patch-wise Cross-Attention (PCA) and Adaptive Gating (AG) to encourage mutual rectification among different modalities. This process simultaneously explores commonalities across modalities while maintaining the uniqueness of each modality. Furthermore, we design a versatile intermediate fusion framework that can leverage CPCF to enhance the performance of multi-modal object detection. The proposed method is extensively evaluated on multiple public multi-modal datasets, namely FLIR, LLVIP, and DroneVehicle. The experiments indicate that our method yields consistent performance gains across various benchmarks and can be extended to different types of detectors, further demonstrating its robustness and generalizability. Our codes are available athttps://github.com/Superjie13/CPCF_Multispectral.

The development of a real-world Unmanned Aircraft System (UAS) Traffic Management (UTM) system to ensure the safe integration of Unmanned Aerial Vehicles (UAVs) in low altitude airspace, has recently generated novel research challenges. A key problem is the development of Pre-Flight Conflict Detection and Resolution (CDR) methods that provide collision-free flight paths to all UAVs before their takeoff. Such problem can be represented as a Multi-Agent Path Finding (MAPF) problem. Currently, most MAPF methods assume that the UTM system is a centralized entity in charge of CDR. However, recent discussions on UTM suggest that such centralized control might not be practical or desirable. Therefore, we explore Pre-Flight CDR methods where independent UAS Service Providers (UASSPs) with their own interests, communicate with each other to resolve conflicts among their UAV operations—without centralized UTM directives. We propose a novel MAPF model that supports the decentralized resolution of conflicts, whereby different ‘agents’, here UASSPs, manage their UAV operations. We present two approaches: (1) a prioritization approach and (2) a simple yet practical pairwise negotiation approach where UASSPs agents determine an agreement to solve conflicts between their UAV operations. We evaluate the performance of our proposed approaches with simulation scenarios based on a consultancy study of predicted UAV traffic for delivery services in Sendai, Japan, 2030. We demonstrate that our negotiation approach improves the “fairness” between UASSPs, i.e. the distribution of costs between UASSPs in terms of total delays and rejected operations due to replanning is more balanced when compared to the prioritization approach.

New technological developments in the field of multimodal interaction show great promise for the improvement and assessment of public speaking skills. However, it is unclear how the experience of non-native speakers interacting with such technologies differs from native speakers. In particular, non-native speakers could benefit less from training with multimodal systems compared to native speakers. Additionally, machine learning models trained for the automatic assessment of public speaking ability on data of native speakers might not be performing well for assessing the performance of non-native speakers. In this paper, we investigate two aspects related to the performance and evaluation of multimodal interaction technologies designed for the improvement and assessment of public speaking between a population of English native speakers and a population of non-native English speakers. Firstly, we compare the experiences and training outcomes of these two populations interacting with a virtual audience system designed for training public speaking ability, collecting a dataset of public speaking presentations in the process. Secondly, using this dataset, we build regression models for predicting public speaking performance on both populations and evaluate these models, both on the population they were trained on and on how they generalize to the second population.

Multiplayer games are an important and popular game mode for networked players. Since games are played by a diverse audience, it is important to scale the difficulty, or challenge, according to the skill level of the players. However, current approaches to real-time challenge balancing (RCB) in games are only applicable to single-player scenarios. In multiplayer scenarios, players with different skill levels may be present in the same area, and hence adjusting the game difficulty to match the skill of one player may affect the other players in an undesirable way. To address this problem, we have previously developed a new approach based on distributed constraint optimization, which achieves the optimal challenge level for multiple players in real-time. The main contribution of this paper is an experiment that was performed with our new multiplayer real-time challenge balancing method applied to eco-driving. The results of the experiment suggest the effectiveness of RCB.

We have developed an interactive virtual audience platform for public speaking training. Users' public speaking behavior is automatically analyzed using multimodal sensors, and ultimodal feedback is produced by virtual characters and generic visual widgets depending on the user's behavior. The flexibility of our system allows to compare different interaction mediums (e.g. virtual reality vs normal interaction), social situations (e.g. one-on-one meetings vs large audiences) and trained behaviors (e.g. general public speaking performance vs specific behaviors).

In this article, we introduce a compositional linguistic approach for attitude recognition in text. There are several aspects that distinguish our attitude analysis model (@AM) from other systems. First, our method classifies sentences using fine‐grained attitude labels (nine for affective states, two for positive and negative judgment, and two for positive and negative appreciation), as compared against other methods that mainly focus on two sentiment categories (positive and negative) or basic emotions. Next, our @AM is based on the analysis of syntactic and dependence relations between words in a sentence, the compositionality principle, a novel linguistic approach based on the rules elaborated for semantically distinct verb classes, and a method considering the hierarchy of concepts. As distinct from the state‐of‐the‐art approaches, the proposed method extensively deals with the semantics of terms, processes sentences of different complexity, handles not only correctly written text but also informal messages, and encodes the strength and the level of confidence of attitude through numerical values. The performance of our @AM was evaluated on data sets represented by sentences from different domains. @AM achieved a high level of accuracy on sentences from personal stories about life experiences, fairy tales, and news headlines, outperforming other methods on several measures.

An important requirement of household energy simulation models is their accuracy in estimating energy demand and its fluctuations. Occupant behavior has a major impact upon energy demand. However, Markov chains, the traditional approach to model occupant behavior, (1) has limitations in accurately capturing the coordinated behavior of occupants and (2) is prone to over-fitting. To address these issues, we propose a novel approach that relies on a combination of data mining techniques. The core idea of our model is to determine the behavior of occupants based on nearest neighbor comparison over a database of sample data. Importantly, the model takes into account features related to the coordination of occupants' activities. We use a customized distance function suited for mixed categorical and numerical data. Further, association rule learning allows us to capture the coordination between occupants. Using real data from four households in Japan we are able to show that our model outperforms the traditional Markov chain model with respect to occupant coordination and generalization of behavior patterns.

This article describes a novel intelligent interface for attitude sensing in text driven by a robust computational tool for the analysis of fine-grained attitudes (emotions, judgments, and appreciations) expressed in text. The module responsible for textual attitude analysis was developed using a compositional linguistic approach based on the attitude-conveying lexicon, the analysis of syntactic and dependency relations between words in a sentence, the compositionality principle applied at various grammatical levels, the rules elaborated for semantically distinct verb classes, and a method considering the hierarchy of concepts. The performance of this module was evaluated on sentences from personal stories about life experiences. The developed web-based interface supports recognition of nine emotions, positive and negative judgments, and positive and negative appreciations conveyed in text. It allows users to adjust parameters, to enable or disable various functionality components of the algorithm, and to select the format of text annotation and attitude statistics visualization.

We present a new framework for conducting controlled driving behavior studies based on multiuser networked 3-D virtual environments. The framework supports: 1) the simulation of multiuser immersive driving; 2) the visualization of surrounding traffic; 3) the specification and creation of reproducible traffic scenarios; and 4) the collection of meaningful driving behavior data. We use our framework to investigate the “rubbernecking” phenomenon, which refers to the slowing down of a driver due to an accident on the opposite side of the road, and its effect on the following drivers. The main contribution of the paper is the Scenario Markup Language (SML) framework, which is composed of: 1) the SML as a practical tool to specify dynamic traffic situations (e.g., an accident) and 2) the Scenario Control System to ensure the reproducibility of particular traffic situations, so that traffic engineers can obtain comparable data and draw valid conclusions. To demonstrate the effectiveness of our framework, we specified the traffic accident scenario in SML and conducted a study about the rubbernecking phenomenon. We report on the results of our study from two viewpoints: 1) the reproducibility of the traffic accident situation (i.e., state variables of interest are recreated successfully in 78% of the cases); and 2) the interactive car-following behavior of human subjects embedded in the traffic situation of the virtual environment.

We present the Scenario Markup Language (SML), a powerful language for authoring realistic traffic situations. This effort is part of a novel framework for automatically generating complex scenarios with static and dynamic elements. SML facilitates the scripting of behavioral driver studies in networked multi-user online three-dimensional (3D) virtual worlds.

Abstract In this paper, we address the tasks of recognition and interpretation of affect communicated through text messaging in online communication environments. Specifically, we focus on Instant Messaging (IM) or blogs, where people use an informal or garbled style of writing. We introduced a novel rule-based linguistic approach for affect recognition from text. Our Affect Analysis Model (AAM) was designed to deal with not only grammatically and syntactically correct textual input, but also informal messages written in an abbreviated or expressive manner. The proposed rule-based approach processes each sentence in stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses) and complex–compound sentences. Affect in text is classified into nine emotion categories (or neutral). The strength of the resulting emotional state depends on vectors of emotional words, relations among them, tense of the analysed sentence and availability of first person pronouns. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize fine-grained emotions reflected in sentences from diary-like blog posts (averaged accuracy is up to 77 per cent), fairy tales (averaged accuracy is up to 70.2 per cent) and news headlines (our algorithm outperformed eight other systems on several measures).

In this paper, we describe methods to automatically generate and score a new sentiment lexicon, called SentiFul, and expand it through direct synonymy and antonymy relations, hyponymy relations, derivation, and compounding with known lexical units. We propose to distinguish four types of affixes (used to derive new words) depending on the role they play with regard to sentiment features: propagating, reversing, intensifying, and weakening. Besides derivation, we considered important process of finding new words such as compounding, which is a highly productive process, especially in the case of nouns and adjectives. We elaborated the algorithm for automatic extraction of new sentiment-related compounds from WordNet using words from SentiFul as seeds for sentiment-carrying base components and applying the patterns of compound formations. In the paper, the importance of considering modifiers, contextual valence shifters, and modal operators, which are integral parts of the SentiFul lexicon for robust sentiment analysis, is also discussed.

The aim of this paper is two-fold. First, it describes a scripting language for specifying communicative behavior and interaction of computer-controlled agents ("bots") in the popular three-dimensional (3D) multiuser online world of "Second Life" and the emerging "OpenSimulator" project. While tools for designing avatars and in-world objects in Second Life exist, technology for nonprogrammer content creators of scenarios involving scripted agents is currently missing. Therefore, we have implemented new client software that controls bots based on the Multimodal Presentation Markup Language 3D (MPML3D), a highly expressive XML-based scripting language for controlling the verbal and nonverbal behavior of interacting animated agents. Second, the paper compares Second Life and OpenSimulator platforms and discusses the merits and limitations of each from the perspective of agent control. Here, we also conducted a small study that compares the network performance of both platforms.

In Mobile Social Networks(MSN) individuals with similar interests or commonalities, connect to each other using the mobile phones. Validation of protocols for these networks relies almost exclusively on simulations. Thus a simulation using a mobility model that captures the behavior of nodes in the real world is needed. The current simulations techniques use random models to generate dynamic MSN. However, the random models are not suitable for MSN simulations. In this paper we use Second Life(SL)1 as a simulation environment, which can support dynamics in simulation models by allowing real users to participate using their avatars. SL is a virtual world simulator accessible via the Internet having more than five hundred thousand active users. SL can capture dynamics of movement models as avatars have different movement speed, different movement patterns and different neighbors. Therefore, in this paper we propose the Virtual Social Simulated Environment (VSSE). VSSE consists of basic simulation using SL Bots (computer controlled SL agents) and protocols to allow avatars to participate in the simulation. Thus making it a participatory MSN simulation environment. We present the design of our state-driven grid region, a prototype implementation based on the daily mobility patterns and compare our system with a similar real-world experiment. To the best of our knowledge this is the first time that a participatory MSN simulations environment has been proposed, which allows anyone, including non-experts, to experiment and experience the technology. Moreover, this approach allows to validate protocols by providing a close to real life simulation environment for researchers.

In this paper we study the problem of message duplication in dissemination of dynamic content such as news or traffic information over a Dense Mobile Social Network (MSN). In MSNs mobile devices disseminate content only to the nodes whose subscribed interest match it. MSNs are used to improve the coverage and increase capacity as we assume that people in an intermittently connected MSNs are socially-related and tend to co-locate quite regularly. MSNs are similar to Disruption Tolerant Networks (DTNs) expect that in MSNs the assumption is that individuals follow predictable working day movement model and the users exchange profile and disseminate content only to the users in their social network. The analysis of three independent experiments conducted, shows that the current message forwarding protocols for dense MSNs can experience up-to 94% of duplicate messages in the worst-case because the messages are replicated to be routed over multiple delivery paths in-order to optimize the probability of successful message delivery. Although these approaches do (statistically) guarantee delivery probability but impose overheads on bandwidth, energy and memory. Therefore, in this paper we propose a message duplication reduction algorithm by exploiting the mobility predictability property of the users in MSNs. We model our problem as an on-line graph and solve the problem of message duplication by an algorithm on the well-known spanning tree problem. Furthermore, we divide our problem into three optimization problems and priorities them as minimize message delivery time, minimize message duplication and minimize message storage space. The study presented in this paper achieve message duplication reduction of 71.8% in the best-case (i.e. domination set of most influential users and many to many data delivery) and 14.8% in the worst case (i.e. selecting random users and one to one data delivery) while guaranteeing a given delay or delivery probability and lowering system wide traffic flooding.

Agriculture has a strong impact in the environment; it has played key role in the development of food security and food safety. In this paper, we are proposing a 3D multilingual Internet game, developed by using the on-line virtual world platform, that lets the player experience the potential effects of agriculture in the environment. The main idea is to foster awareness of agriculture's environmental issues, by not only making the player learn the impact of fertilizers and deforestation that affect the sources of water and weather, respectively, but also enhance the importance of food quality. To make players care for these issues, the game creates a direct impact by using the happiness of people that is represent by the villagers. To reduce the language barrier when sharing knowledge across the countries is needed, the game also supports multi-language to make it more understandable to the player. This paper describes details of the game design, the system architecture and the experiment. The experiment conducted with the game showed promising results.

The sharing of academic knowledge through printed publications has been widely and successfully utilized for more than a hundred years. However, the need to process huge amounts of data in scientific analysis and communicate its results to the scientific community has presented a big challenge for researchers in the data-intensive era. In addition to providing accurate and flexible graphical representations of data, the entire research process should ideally be made verifiable by peers. While web-based tools have been proposed to address this problem, most of them lack important features for scientific work such as real-time collaboration, powerful multimedia visualization and interaction, and environment persistency. Therefore, in this paper, we will propose the use of virtual world technology to address these issues. In particular, we will give an overview of the different methods that we have implemented in the context of multimedia interaction, which is considered the most critical factor in the development of virtual worlds as sound platforms for human-centered multimedia systems.

News is an interesting application domain for “emotion sensing”, since readers often have a personal attitude or subjective opinion regarding certain events or entities reported about. Hence the ability to determine user-centric emotion on a given to

In this paper, the authors extend previous work on the automatic structuring of medical documents using content analysis. Their long-term objective is to take advantage of specific rhetoric markers encountered in specialized medical documents (clinical guidelines) to automatically structure free text according to its role in the document. This should enable to generate multiple views of the same document depending on the target audience, generate document summaries, as well as facilitating knowledge extraction from text. The authors have established in previous work that the structure of clinical guidelines could be refined through the identification of a limited set of deontic operators. They now propose to extend this approach by analyzing the text delimited by these operators using Rhetorical Structure Theory. The emphasis on causality and time in RST proves a powerful complement to the recognition of deontic structures while retaining the same philosophy of high-level recognition of sentence structure, which can be converted into applicationspecific mark-ups. Throughout the paper, the authors illustrate their findings through results produced by the automatic processing of English guidelines for the management of hypertension and Alzheimer disease.

In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and user-attractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.

In this paper we introduce a system that automatically adds different types of non-verbal behavior to a given dialogue script between two virtual embodied agents. It allows us to transform a dialogue in text format into an agent behavior script enriched by eye gaze and conversational gesture behavior. The agents' gaze behavior is informed by theories of human face-to-face gaze behavior. Gestures are generated based on the analysis of linguistic and contextual information of the input text. The resulting annotated dialogue script is then transformed into the Multimodal Presentation Markup Language for 3D agents (MPML3D), which controls the multi-modal behavior of animated life-like agents, including facial and body animation and synthetic speech. Using our system makes it very easy to add appropriate non-verbal behavior to a given dialogue text, a task that would otherwise be very cumbersome and time consuming.

In this paper, we focus on affect recognition from text in order to facilitate sensitive and expressive communication in computer-mediated environments. Our model for analyzing affect conveyed by text is tailored to handle the style and specifics of informal online conversations. The motivation behind our approach is to improve social interactivity and emotional expressiveness of real-time messaging.In order to estimate affect in text, our model processes symbolic cues, such as emoticons, detects and transforms abbreviations, and employs natural language processing techniques for word/phrase/sentence-level analysis, e.g. by considering relations among words in a sentence. As a result of the analysis, text can be categorized into emotional states and communicative functions. A designed graphical representation of a user (avatar) displays emotions and social behaviour driven by text and performs natural idle movements. The proposed system shows promising results on affect recognition in real examples of online conversation.

This paper describes a character-based system called "Emotion Sensitive News Agent" (ESNA). ESNA is been developed as a news aggregator to fetch news from different news sources chosen by a user, and to categorize the themes of the news into eight emotion types. A small user study indicates that the system is conceived as intelligent and interesting as an affective interface. ESNA exemplifies a recent research agenda that aims at recognizing affective information conveyed through texts. News is an interesting application domain where user may have marked attitudes to certain events or entities reported about. Different approaches have already been employed to "sense" emotion from text. The novelty of our approach is twofold: affective information conveyed through text is analyzed (1) by considering the cognitive and appraisal structure of emotions, and (2) by taking into account user preferences.

We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obtain quantitative evidence of a user’s focus of attention without distracting from the primary task. The salient feature of our evaluation strategy is that it allows us to measure important properties of a user’s interaction experience on a moment-by-moment basis in addition to a cumulative (spatial) analysis of the user’s areas of interest. We describe a pilot study in which we compare attending behavior of subjects watching the presentation of a computer-generated apartment layout and visualization augmented by three types of media: an animated agent, a text box, and speech only. The investigation of eye movements revealed that deictic gestures performed by the agent are more effective in directing the attentional focus of subjects to relevant interface objects than the media used in the two control conditions, at a slight cost of distracting the user from visual inspection of the object of reference. The results also demonstrate that the presence of an interface agent seemingly triggers natural and social interaction protocols of human users.

Studying the relationship between natural language and affective information as well as assessing the underpinned affective qualities of natural language are becoming crucial for improving human computer interaction. Different approaches have already been employed to "sense" affective information from text but none of those considered the cognitive structure of individual emotions and appraisal structure of those emotions adopted by emotion sensing programs. It has also been observed that previous attempts for textual affect sensing have categorized texts into a number of emotion groups, e.g. six so-called "basic" emotion proposed by Paul Ekman which we believe insufficient to classify textual emotions. Hence we propose a different approach to sense affective information from texts by applying the cognitive theory of emotions known as OCC model [1] which distinguishes several emotion types that can be identified by assessing valenced reactions to events, agents or objects described in the texts. In particular we want to create a formal model that can not only "understand" what emotions people wrap with their textual messages, but also can make automatic empathic response with respect to the emotional state detected in the text (e.g. in a chat system). We first briefly describe relevant works and then we explain our proposal with examples. Finally we conclude with future work plans.

We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obtain quantitative evidence of a user's focus of attention. The salient feature of our evaluation strategy is that it allows us to measure important properties of a user's interaction experience on a moment-by-moment basis in addition to a cumulative (spatial) analysis of the user's areas of interest. We describe an empirical study in which we compare attending behavior of subjects watching the presentation of an apartment by three types of media: an animated agent, a text box, and speech only. The investigation of users' eye movements reveals that agent behavior may trigger natural and social interaction behavior of human users.

This second workshop on Multi-User and Ubiquitous User Interfaces aims at further investigating two major issues identified at last year's MU3I: control and consistency. The former relates to how a user gains control of devices in a ubiquitous computing environment, how control is passed, and how it is shared in such a setting. The second one concerns interfaces that span multiple devices or move from one set of devices to another. Both issues will be discussed in this year's workshop (with a focus on consistency.

This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. As a novel feature, social role awareness is introduced to animated conversational agents, that are by non-strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behavior depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a "social filter program" to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social contest, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.

We present an approach to knowledge compilation that transforms a function-free first-order Horn knowledge base to propositional logic. This form of compilation is important since the most efficient reasoning methods are defined for propositional logic, while knowledge is most conveniently expressed within a first-order language. To obtain compact propositional representations, we employ techniques from (ir)relevance reasoning as well as theory transformation via unfold/fold transformations. Application areas include diagnosis, planning, and vision. Preliminary experiments with a hypothetical reasoner indicate that our method may yield significant speed-ups.