Electrical & Computer Engineering

Interactive entertainment permits users to participate actively. In this paper, we consider the importance of cinematic presentation in internet-based interactive entertainment. We propose that a tool for the artistic and technical representation of presentation-layer demands of interactive entertainment already exists: a system called DirectorNotation. This system can provide the ability for the creation of artistically significant, adaptive, context sensitive, interactive, actionable multimedia content. In the work that has been presented so far on DirectorNotation, the applications that are considered target the professional film director in his filming activities to produce better results, or consider the “Artificial Intelligence” possibilities of exploiting a knowledge model of film directing. In this paper, we aim to create a connection to the domain of interactive entertainment, showing that this application area can achieve highly promising improvements by exploiting the suggested technology combination.

Nowadays, computer games entertain millions of computer users. They support incredible 3D graphics that attract players. However, cinematic presentation in computer games is missing. There are technologies and rules for camerawork and lighting that are not exploited by game engines. In this paper, we demonstrate some problems that computer games suffer from, at the presentation level, and we examine a new research project, called ANSWER, as a potential solution to those problems. ANSWER attempts to cover the expressive needs of film directors and game animators, by providing a set of tools that will allow the description of a game or a film at the artistic level and during its production phase.

In the present paper we explore Ontologies, as a means to capture knowledge of the film-making domain. More specifically, we intend to open a discussion so as to guide the development of DirectorNotation, an under-development open-source tool for representing media content, as of its pre-production and production phases, using a symbolic notation system, in which a film director can formally record his intentions. DirectorNotation’s authors suggest Ontologies for formalizing and reasoning over their notation system. The current paper discusses this technical choice, considering its limitations, and makes suggestions about the work that needs to be performed if these limitations are to be overcome.

Within the scope of ANSWER, an EC-supported research project, a new artistic notation system, called DirectorNotation, is being developed for describing media content, much like notes are used to document a music composition. Our current research focuses on developing “notation-enabled” offline authoring tools, but interactive applications are an anticipated extension. Here, we summarise the key aspects of DirectorNotation and the ANSWER project, from the point of view of a multimedia-technology audience interested in content-based manipulation of media.

Recent advances in Affective Computing (AC) include research towards automatic analysis of human emotionally enhanced behavior during multiparty interactions within different contextual settings. Current paper delves on how is context incorporated into multiparty and multimodal interaction within the AC framework. Aspects of context incorporation such as importance and motivation for context incorporation, appropriate emotional models, resources of multiparty interactions useful for context analysis, context as another modality in multimodal AC and context-aware AC systems are addressed as research questions reviewing the current state-of-the-art in the research field. Challenges that arise from the incorporation of context are identified and discussed in order to foresee future research directions in the domain. Finally, we propose a context incorporation architecture into affect-aware systems with multiparty interaction including detection and extraction of semantic context concepts, enhancing emotional models with context information and context concept representation in appraisal estimation.

In the emerging Smart Cities-Smart Homes computing paradigms developing a formalization for context information is increasingly important. In the present paper, basedon the EU FIRE research project " Social and Smart " we aim to formalize and build a complete formal definition of context in both home and city scale. Using sensors as a Smart City service and local sensors installed locally in Smart Homes, it is possible to collect continuously context data, such as temperature, humidity, noise and pollution levels. This context information can be used to adapt to user-specific needs in the Smart Home environment via the incorporation of user defined home rules. Semantic web technologies are used to support the knowledge representation of this ecosystem. The overall architecture has been experimentally verified using input from the SmartSantander Smart City project and applying it to the SandS Smart Home within the FIRE and * George Caridakis is also affiliated with the FIWARE framework. Finally, two examples are presented in order to stress how the smart home appliances adapt their function to home rules and context information.

This paper presents an overview on how an ecosystem, consisted of users, appliances and environmental context interacts. The ecosystem is modeled by using Semantic Web technologies from the Internet of Things (IoT) perspective. The IoT is made of users, appliances, sensors and houses. Users are modeled as fuzzy personas and these models are semantically related. Semantic Web technologies enhance the system with adaptability and assist the incorporation of environmental context, user and usage information. Context information consists of temperature, humidity and luminos-ity and information about infrastructure reconfiguration and user location. This information is collected from various IoT sensors, in the pervasive and urban environment and stored into a repository for rule triggering and system adaptation. Experiments were conducted in order to validate the effectiveness of the proposed system both in the restricted scale of a smart home as well as in a larger scale using input from the SmartSantander Smart City project, collected using the FIWARE framework.

This paper investigates a method based on Conditional Random Fields (CRFs) to incorporate sentence structure (syntax and semantics) and context information to identify sentiments of sentences. It also demonstrates the usefulness of the Rhetorical Structure Theory (RST) taking into consideration the discourse role of text segments. Thus, this paper's aim is to reconsider the effectiveness of CRF and RST methods in incorporating the contextual information into Sentiment Analysis systems. Both methods are evaluated on two, different in size and genre of information sources, the Movie Review Dataset and the Finegrained Sentiment Dataset (FSD). Finally, we discuss the lessons learned from these experimental settings w.r.t. addressing the following key research questions such as whether there is an appropriate type of social media repository to incorporate contextual information, whether extending the pool of the selected features could improve context incorporation into SA systems and which is the best performing feature combination to achieve such improved performance.

One of the main challenges of recent years is to create Affective-aware Human Computer Interaction (HCI)
systems and context-aware Affective Computing (AC) systems. But, what does it mean to create or advance
such systems when incorporating context features and which should be the most appropriate type of such
context features? Even though a number of studies have analyzed how different features, when incorporated
into AC systems and particular into Sentiment Analysis (SA) systems, improve their performance; a complete
picture of their effectiveness remains unexplored. So far, a wide range of context-aware features has been
independently tested by a large number of research teams, mostly in constrained settings (Beineke et al. 2004,
Pang et al. 2004, Pang et al. 2002, Turney 2002). Nevertheless, there is not a clear picture of the impact of
every feature set and there is little to no evidence regarding how the combination of such context-aware
features behaves with different in size and genre of information sources. In light of these observations, we
attempt to extend the pool of the context-aware sentence features used into context-aware SA and to further
provide the foundations for a comprehensive analysis of the relative importance of the various types of
contextual features.

This paper investigates the problem of context incorporation into human language systems and particular in Sentiment Analysis (SA) systems. So far, the analysis of how different features, when incorporated into such systems, improve their performance, has been discussed in a number of studies. However, a complete picture of their effectiveness remains unexplored. With this work, we attempt to extend the pool of the context-aware language features at the sentence level and to provide the foundations for a concise analysis of the importance of the various types of contextual features, using data from two different in type and size datasets: the Movie Review Dataset (MR) and the Finegrained Sentiment Dataset (FSD).