Dialogue Tree Research Articles

An Educational Chatbot Using AI in Radiotherapy

The surge in demand for information in cancer centers and hospitals, particularly during the pandemic, overwhelmed the limited manpower available. To address this challenge, there arose a need to develop an educational chatbot tailored for diverse user groups in the field of radiotherapy, including patients and their families, the general public, and radiation staff. Objective: In response to the pressing clinical demands, the primary aim of this endeavor is to delve into the intricacies of designing an educational chatbot for radiotherapy using artificial intelligence.Methods: The chatbot is meticulously crafted using a dialogue tree and layered structure, seamlessly integrated with artificial intelligence functionalities, notably natural language processing (NLP). This adaptable chatbot can be deployed across various platforms, such as IBM Watson Assistant, and embedded in websites or diverse social media channels.Results: Employing a question-and-answer methodology, the chatbot adeptly engages users seeking information on radiotherapy, presenting an approachable and reassuring interface. Recognizing that users, often anxious, may struggle to articulate precise questions, the chatbot facilitates the interaction by offering a curated list of questions. The NLP system augments the chatbot's ability to discern user intent, ensuring the provision of accurate and targeted responses. Notably, the study reveals that functional features, including mathematical operations, are preferred in educational chatbots, necessitating routine updates to furnish fresh content and features.Conclusions: The study culminates in the affirmation that leveraging artificial intelligence facilitates the creation of an educational chatbot capable of disseminating information to users with diverse backgrounds in radiotherapy. Furthermore, the importance of rigorous testing and evaluation, informed by user feedback, is emphasized to iteratively enhance and refine the chatbot's performance. Keywords: AI, machine learning, NLP, chatbot, radiotherapy, IoT, healthcare.

Enhancing Listening Skill Through Narrative Text in Video Games

This research aims to discover the types of narrative text through listening to video games. The research focuses focusing enhancing students’ listening skills through narrative text appearing in video games and how listening can be enhanced by narrative text video games. This research uses a qualitative descriptive method. The researcher collected some data through the video games and then continued to classify them into narrative text analysis, especially linear structure, and branch structure. The researcher employed E. Kleinman Carstensdottir and M.S El-Nasr’s theory to analyze the texts and filter them into the linear structure and branch structure categories. The results show that linear structures have cutscenes, character interactions, and task completion. The video games that represent this analysis to enhance listening are taken from Alan Wake 2. The branch structures have multiple endings, dialogue trees, and quick-times events. The video games that represent this analysis to enhance listening are taken from Detroit: Become Human. This analysis shows that narrative video games provide an effective and leisurely way for individuals to practice and enhance their listening skill.

Design of an Educational Chatbot Using Artificial Intelligence in Radiotherapy

Context: In cancer centres and hospitals particularly during the pandemic, there was a great demand for information, which could hardly be handled by the limited manpower available. This necessitated the development of an educational chatbot to disseminate topics in radiotherapy customized for various user groups, such as patients and their families, the general public and radiation staff. Objective: In response to the clinical demands, the objective of this work is to explore how to design a chatbot for educational purposes in radiotherapy using artificial intelligence. Methods: The chatbot is designed using the dialogue tree and layered structure, incorporated with artificial intelligence features such as natural language processing (NLP). This chatbot can be created in most platforms such as the IBM Watson Assistant and deposited in a website or various social media. Results: Based on the question-and-answer approach, the chatbot can provide humanlike communication to users requesting information on radiotherapy. At times, the user, often worried, may not be able to pinpoint the question exactly. Thus, the chatbot will be user friendly and reassuring, offering a list of questions for the user to select. The NLP system helps the chatbot to predict the intent of the user so as to provide the most accurate and precise response to him or her. It is found that the preferred educational features in a chatbot are functional features such as mathematical operations, which should be updated and modified routinely to provide new contents and features. Conclusions: It is concluded that an educational chatbot can be created using artificial intelligence to provide information transfer to users with different backgrounds in radiotherapy. In addition, testing and evaluating the performance of the chatbot is important, in response to user’s feedback to further upgrade and fine-tune the chatbot.

Linguistic Environments of Digital Games

This study quantitatively measures the variation in language derived from a targeted set of digital game mechanics. Mechanics refer to the design elements of a game that make up the overall gameplay experience, determining player actions and the degree of language interaction. A corpus was compiled by extracting the language files from two popular commercial games, Fallout 4 and Skyrim, using modification software. The extracted language files were organized into three register categories following the register analysis framework detailed in Biber and Conrad (2019). The three categories include one spoken (dialogue trees) and two written registers (quest objectives and quest stages), which are common mechanics in many modern commercial games. Comparing results from three discriminant analyses, the findings indicate that statistical models cannot distinguish between the two games’ linguistic environments at the level of the game; however, when considering the linguistic environments at the level of game mechanics, the model has high precision in accurately identifying the texts’ game mechanic register categories. The results provide empirical evidence that digital game-based language learning (DGBLL) research designs could benefit from targeting specific design aspects and game mechanics rather than generalizing results at the level of genre or game title.

Intelligent Cognitive Assistants for Attitude and Behavior Change Support in Mental Health: State-of-the-Art Technical Review

Intelligent cognitive assistant (ICA) technology is used in various domains to emulate human behavior expressed through synchronous communication, especially written conversation. Due to their ability to use individually tailored natural language, they present a powerful vessel to support attitude and behavior change. Behavior change support systems are emerging as a crucial tool in digital mental health services, and ICAs exceed in effective support, especially for stress, anxiety and depression (SAD), where ICAs guide people’s thought processes and actions by analyzing their affective and cognitive phenomena. Currently, there is no comprehensive review of such ICAs from a technical standpoint, and existing work is conducted exclusively from a psychological or medical perspective. This technical state-of-the-art review tried to discern and systematize current technological approaches and trends as well as detail the highly interdisciplinary landscape of intersections between ICAs, attitude and behavior change, and mental health, focusing on text-based ICAs for SAD. Ten papers with systems, fitting our criteria, were selected. The systems varied significantly in their approaches, with the most successful opting for comprehensive user models, classification-based assessment, personalized intervention, and dialogue tree conversational models.

Embedding scientific information into forestry praxis: Explaining knowledge transfer in transdisciplinary projects by using German case

The Horizon 2020 project, ALTERFOR, generated knowledge about forest management alternatives. Researchers modelled a future, sustainable provision of ecosystem services, where a salient question was one of how to facilitate the application of these innovative scientific results in praxis. Our qualitative study uses a method mix and the analytical Research-Integration-Utilisation (RIU) Model to provide in-depth explanation of the knowledge transfer going on between the ALTERFOR research project and the forestry praxis. The leading assumption related to this communication process is that selected pieces of information are de-embedded from their scientific context of the research project and re-embedded into the existing knowledge of specific forestry actors, who utilise them to implement science-based management solutions in their forest. This assumption is empirically corroborated by using ALTERFOR's German case. For the approximately 100, 000 ha of Augsburg Western Woods (south-western Bavaria) the researchers simulated five scenarios, showing which ecosystem services would be provided by different forest management models over the next 100 years. The integration of scenario results into the praxis comprised three integration forums. Within the first forum (pre-study) the alternatives focusing on “recreation” and “hunting” were dropped due to a lack of supportive powerful allies from praxis. Within the second forum (bilateral meeting) the three other scenarios - “timber production”, “multifunctional” and “set aside” scenarios, all remained in the discourse of praxis. Yet, the third forum (multilateral meeting - workshop) triggered the toughest selection. Most project results were either ignored or declined strongly, so that only a few pieces of scientific information found acceptance by particular actors, who utilised them either through support or resistance: (i) the State Forest used the information about the “multifunctional” scenario to legitimise the solution which was already in use (multifunctional management), whereas the Private Forest used the information for the possibility to increase timber harvests in a sustainable way, in order to push for (an otherwise contested) strategy of maximized timber harvesting; (ii) the State Forest resisted the possibility of increasing sustainable timber harvesting, whereas the Private Forest rejected the implementation of set asides. Both actors had sufficient power capabilities to realise their interests, even against the interests of other landowners or political groups. These results show that it is not complex scientific knowledge that makes it through the selection process, but rather, pieces of scientific information, de-embedded from their theory-based context of the research project, are re-embedded into the context of powerful actors in praxis, who then utilise these to either support or resist their own science-based solutions. Based on this, we suggest that the ambitious Horizon 2020 goal of facilitating knowledge transfer is attained more effectively when the project opens up multiple options for dialogue between researchers and different groups from praxis (multi-actor approach), abandoning the idea of one, best solution and offering different alternatives instead.

Higher order functions and Brouwer’s thesis

AbstractExtending Martín Escardó’seffectful forcingtechnique, we give a new proof of a well-known result: Brouwer’s monotone bar theorem holds for any bar that can be realized by a functional of type (ℕ→ℕ)→ℕ in Gödel’sSystem T. Effectful forcing is an elementary alternative to standard sheaf-theoretic forcing arguments, using ideas from programming languages, including computational effects, monads, the algebra interpretation of call-by-name λ-calculus, and logical relations.Our argument proceeds by interpretingSystem Tprograms as well-founded dialogue trees whose nodes branch on a query to an oracle of type ℕ→ℕ, lifted to higher type along a call-by-name translation. To connect this interpretation to the bar theorem, we then show that Brouwer’s famous “mental constructions” of barhood constitute an invariant form of these dialogue trees in which queries to the oracle are made maximally and in order.

Research on the Path of Science and Technology Supporting the Construction of Jiangsu Modern Marine Economic System

Song, S.; Wang, X., and Su, C., 2019. Research on the path of science and technology supporting the construction of Jiangsu modern marine economic system. In: Li, L.; Wan, X.; and Huang, X. (eds.), Recent Developments in Practices and Research in Coastal Regions: Transportation, Environment, and Economy, Journal of Coastal Research, Special Issue No. 98, pp. 179–182. Coconut Creek (Florida), ISSN 0749-0208.Research on the construction path of marine economic system is a kind of exploration of behavior based on data flow among the regional economies in the Inner Mongolia area. In this paper, the Dijstra algorithm is combined to explore the regional economic development gap and the coordinated development path in the Inner Mongolia area. Through several preconditions and a conclusion, the defeasible rule for the effective tender can be obtained. In addition, the process of deduction is explored through the dialogue tree. Verification and analysis on the algorithm are carried out through instances. The final result shows that, for the Jiangsu modern marine economy, the algorithm put forward in this paper can be used to implement exploration on the regional economic development gap and the coordinated development path in the Inner Mongolia area.

Representing definable functions of HAω by neighbourhood functions

Brouwer (1927) claimed that every function from the Baire space to natural numbers is induced by a neighbourhood function whose domain admits bar induction. We show that Brouwer's claim is provable in Heyting arithmetic in all finite types (HAω) for definable functions of the system. The proof does not rely on elaborate proof theoretic methods such as normalisation or ordinal analysis. Instead, we internalise in HAω the dialogue tree interpretation of Gödel's system T due to Escardó (2013). The interpretation determines a syntactic translation of terms, which yields a neighbourhood function from a closed term of HAω with the required property. As applications of this result, we prove some well-known properties of HAω: uniform continuity of definable functions from NN to N on the Cantor space; closure under the rule of bar induction; and closure of bar recursion for the lowest type with a definable stopping function.

Introductory dialogue and the Köhler Effect in software-generated workout partners

ObjectivesThis study explored the Köhler motivation gain effect utilizing adults and software-generated partners (SGPs) during an abdominal exercise regimen and compared the type of participant-SGP introductory dialogue as a moderator. The Köhler effect applies interdependent team dynamics in which group performance is dependent upon the weaker member. The third objective was to examine if this motivation paradigm would result in adverse consequences to secondary variables: exertion, enjoyment, and self-efficacy beliefs. DesignAdults (Mage = 38.8 ± 7.7) were randomly assigned to 1 of 3 conditions: Interactive Partner SGP (IP), Linear Dialogue Partner SGP (LDP), or individual control (IC), to complete a series of abdominal exercises. The experiment used a 3 (condition) x 2 (gender) ANCOVA design, with a baseline block of exercises as a covariate. MethodParticipants completed abdominal exercises individually and, after a rest, repeated the same exercises with either an SGP programmed to be moderately stronger or individually (IC). Prior to the second exercise block, IP participants interacted with the SGP using a dialogue tree optional-response format. The LDP participant introduction was a linear, scripted exchange of basic information. ResultsThe LDP and IP conditions persisted significantly longer than IC, generating moderate effect sizes (d = 0.62; d = 0.76). The mean difference between partnered conditions was not significant. ConclusionsThe Köhler motivation exercise paradigm resulted in a considerable increase in persistence (Madj = 28.9, SE = 10.6) in the first study to use middle-aged adults with superior SGPs. Differences between introductory dialogue methods were not significant.

A Step Towards the Future of Role-Playing Games: The SpyFeet Mobile RPG Project

Meaningful choice has often been identified as a key component in a player's engagement with an interactive narrative, but branching stories require tremendous amounts of hand-authored content, in amounts that increase exponentially rather than linearly as more choice points are added. Previous approaches to reducing authorial burden for computer RPGs have relied on creating better tools to manage existing unwieldy structures of quests and dialogue trees. We hypothesize that reducing authorial burden and increasing agency are two sides of the same coin, requiring specific advancements in two related areas of design and technology research: (1) dynamic story management architecture that represents story events abstractly and allows story elements to be selected and re-ordered in response to player choices, and (2) dynamic dialogue generation to allow a single story event to be revealed differently by different characters and in the context of dynamic relationships between those characters and the player. This paper describes SpyFeet, a playable prototype of a storytellingsystem designed to test this hypothesis.

A Dynamic Spoken Dialogue Interface for Ambient Intelligence Interaction

In this paper, we present the interpretation and generation processes of a spoken dialogue interface for ambient intelligence. The interface is automatically created for each specific environment and the interpretation and generation vary depending on the environment and its context. These processes rely on a dialogue tree structure. Several modules process the tree structure and the context information to produce specific dialogues for the current environment state. The interface has been implemented and evaluated in an ambient intelligence environment. Satisfactory objective and subjective evaluation results are shown at the end of the paper.

A parameterised hierarchy of argumentation semantics for extended logic programming and its application to the well-founded semantics

Argumentation has proved a useful tool in defining formal semantics for assumption-based reasoning by viewing a proof as a process in which proponents and opponents attack each others arguments by undercuts (attack to an argument's premise) and rebuts (attack to an argument's conclusion). In this paper, we formulate a variety of notions of attack for extended logic programs from combinations of undercuts and rebuts and define a general hierarchy of argumentation semantics parameterised by the notions of attack chosen by proponent and opponent. We prove the equivalence and subset relationships between the semantics and examine some essential properties concerning consistency and the coherence principle, which relates default negation and explicit negation. Most significantly, we place existing semantics put forward in the literature in our hierarchy and identify a particular argumentation semantics for which we prove equivalence to the paraconsistent well-founded semantics with explicit negation, WFSX. Finally, we present a general proof theory, based on dialogue trees, and show that it is sound and complete with respect to the argumentation semantics.

A model for habitable and efficient dialogue management for natural language interaction

Natural language interfaces require dialogue models that allow for robust, habitable and efficient interaction. This paper presents such a model for dialogue management for natural language interfaces. The model is based on empirical studies of human computer interaction in various simple service applications. It is shown that for applications belonging to this class the dialogue can be handled using fairly simple means. The interaction can be modeled in a dialogue grammar with information on the functional role of an utterance as conveyed in the linguistic structure. Focusing is handled using dialogue objects recorded in a dialogue tree representing the constituents of the dialogue. The dialogue objects in the dialogue tree can be accessed by the various modules for interpretation, generation and background system access. Focused entities are modeled in entities pertaining to objects or sets of objects, and related domain concept information; properties of the domain objects. A simple copying principle, where a new dialogue object's focal parameters are instantiated with information from the preceding dialogue object, accounts for most context dependent utterances. The action to be carried out by the interface is determined on the basis of how the objects and related properties are specified. This in turn depends on information presented in the user utterance, context information from the dialogue tree and information in the domain model. The use of dialogue objects facilitates customization to the sublanguage utilized in a specific application. The framework has successfully been applied to various background systems and interaction modalities. In the paper results from the customization of the dialogue manager to three typed interaction applications are presented together with results from applying the model to two applications utilizing spoken interaction.

The trauma triangle

Recent research supports the hypothesis that more active engagement of the patient in occurring illnesses improves quality of life and probably even life expectancy. In this study experience and theoretical knowledge from psychotherapy is transplanted to clinical practice in order to improve the physician's engagement in the patient-disease relationship. By defining severe and long-term illnesses as a psychotrauma, the transfer of the psychotherapeutical model leads to the creation of a new triangular relationship: patient-illness-doctor. Practical examples are used as illustrations for the conceptual differences between psychotherapy and clinical medicine. Options for dialogue show the difference between adaptation ("learning to live with") and adjustment (active coping strategies and controlling). The hypothesis is that a better dialogue will reduce illness-related stress, giving the patient better and more effective access to personal psychic and physical support systems.