Computer Engineering Commons^™

Technical Report: A Framework For Confusion Mitigation In Task-Oriented Interactions, Na Li, Robert J. Ross

Articles

Confusion is a mental state that can be triggered in task-oriented interactions and which can if left unattended lead to boredom, frustration, or disengagement from the task at hand. Since previous work has demonstrated that confusion can be detected in embodied situated interactions from visual and auditory cues, in this technique report, we propose appropriate interaction structures which should be used to mitigate confusion. We motivate and describe this dialogue mechanism through an information state-style policy with examples, and also outline the approach we are taking to integrate such a meta-conversational goal alongside core task-oriented considerations in modern data driven …

Queer In Ai: A Case Study In Community-Led Participatory Ai, Anaelia Ovalle, Arjun Subramonian, Ashwiin Singh, Claas Voelcker, Danica Sutherland, Davide Locatelli, Eva Breznik, Felip Klubicka, Hang Yuan, Hetvi J, Huan Zhang, Jaidev Shriram, Kruno Lehman, Luca Soldaini, Maarten Sap, Marc Peter Deisenroth, Maria Leonor Pacheco, Maria Ryskina, Martin Mundt, Melind Agarwal, Nyx Mclean, Pan Xu, A. Pranav, Raj Korpan, Ruchira Ray, Sarah Mathew, Sarthak Arora, S.T. John, Tanvi Anand, Vishakha Agrawal, William Agnew, Yanan Long, Zijie J. Wang, Zeerak Talat, Avijit Ghosh, Nathaniel Dennler, Michael Noseworthy, Sharvani Jha, Emi Baylor, Aditya Joshi, Natalia Y. Bilenko, Andrew Mcnamara, Raphael Gontijo-Lopes, Alex Markham, Evyn Dong, Jackie Kay, Manu Saraswat, Nikhil Vytla, Luke Stark

Conference papers

Queerness and queer people face an uncertain future in the face of ever more widely deployed and invasive artificial intelligence (AI). These technologies have caused numerous harms to queer people, including privacy violations, censoring and downranking queer content, exposing queer people and spaces to harassment by making them hypervisible, deadnaming and outing queer people. More broadly, they have violated core tenets of queerness by classifying and controlling queer identities. In response to this, the queer community in AI has organized Queer in AI, a global, decentralized, volunteer-run grassroots organization that employs intersectional and community-led participatory design to build an inclusive …

A Framework For Sexism Detection On Social Media Via Byt5 And Tabnet, Arjumand Younus, Muhammad Atif Qureshi

Articles

Hateful and offensive content on social media platforms particularly content directed towards a specific gender is a great impediment towards equality, diversity and inclusion. Social media platforms are facing increasing pressure to work towards regulation of such content; and this has directed researchers in text mining to work towards hate speech identification algorithms. One such attempt is sexism detection for which mostly transformer-based text methods have been proposed. We propose a combination of byte-level model ByT5 with tabular modeling via TabNet that has at its core an ability to take into account platform and language aspects of the challenging task …

Addressing The "Leaky Pipeline": A Review And Categorisation Of Actions To Recruit And Retain Women In Computing Education, Alina Berry, Susan Mckeever, Brenda Murphy, Sarah Jane Delany

Conference papers

Gender imbalance in computing education is a well-known issue around the world. For example, in the UK and Ireland, less than 20% of the student population in computer science, ICT and related disciplines are women. Similar figures are seen in the labour force in the field across the EU. The term "leaky pipeline"; is often used to describe the lack of retention of women before they progress to senior roles. Numerous initiatives have targeted the problem of the leaky pipeline in recent decades. This paper provides a comprehensive review of initiatives related to techniques used to boost recruitment and improve …

Development Of An Explainability Scale To Evaluate Explainable Artificial Intelligence (Xai) Methods, Stephen Mccarthy

Dissertations

Explainable Artificial Intelligence (XAI) is an area of research that develops methods and techniques to make the results of artificial intelligence understood by humans. In recent years, there has been an increased demand for XAI methods to be developed due to model architectures getting more complicated and government regulations requiring transparency in machine learning models. With this increased demand has come an increased need for instruments to evaluate XAI methods. However, there are few, if none, valid and reliable instruments that take into account human opinion and cover all aspects of explainability. Therefore, this study developed an objective, human-centred questionnaire …

The Evolution Of The Internet And Social Media: A Literature Review, Charles Alves De Castro, Isobel O'Reilly Dr, Aiden Carthy

Articles

This article reviews and analyses factors impacting the evolution of the internet, the web, and social media channels, charting historic trends and highlight recent technological developments. The review comprised a deep search using electronic journal databases. Articles were chosen according to specific criteria with a group of 34 papers and books selected for complete reading and deep analysis. The 34 elements were analysed and processed using NVIVO 12 Pro, enabling the creation of dimensions and categories, codes and nodes, identifying the most frequent words, cluster analysis of the terms, and creating a word cloud based on each word's frequency. The …

Perception Based Misunderstandings In Human-Computer Dialogues, Niels Schütte, John D. Kelleher, Brian Mac Namee

Articles

In a situated dialogue, misunderstandings may arise if the participants perceive or interpret the environment in different ways. In human-computer dialogue this may be due the sensor errors. We present an experiment system and a series of experiments in which we investigate this problem.

A Performance Analysis Of Ws-* (Soap) And Restful Web Services For Implementing Service And Resource Orientated Architectures, Philip Markey, Gary Clynch

Conference Papers

The past number of years have seen the emergence of Service-Oriented Architectures as a dominant architecture for implementing enterprise scale distributed systems. Two main styles of SOA exist, namely SOAP based services and RESTful services. There has been much comment and debate on the pros and cons of each approach to implementing a SOA, a lot of which has surrounded the performance characterictcs of both approaches. In this paper, the authors presents the results of a performance analysis that was conducted on a set of test SOA scenarios implemented using both SOAP and RESTful approaches; in particular the caching capabilities …

A Crowdsourcing Approach To Labelling A Mood Induced Speech Corpus, John Snel, Alexey Tarasov, Charlie Cullen, Sarah Jane Delany

Conference papers

This paper demonstrates the use of crowdsourcing to accumulate ratings from na ̈ıve listeners as a means to provide labels for a naturalistic emotional speech dataset. In order to do so, listening tasks are performed with a rating tool, which is delivered via the web. The rating requirements are based on the classical dimensions, activation and evaluation, presented to the participant as two discretised 5-point scales. Great emphasis is placed on the participant’s overall understanding of the task, and on the ease-of-use of the tool so that labelling accuracy is reinforced. The accumulation process is ongoing with a goal to …

Obtaining Speech Assets For Judgement Analysis On Low-Pass Filtered Emotional Speech, John Snel, Charlie Cullen

Conference papers

Investigating the emotional content in speech from acoustic characteristics requires separating the semantic con- tent from the acoustic channel. For natural emotional speech, a widely used method to separate the two channels is the use of cue masking. Our objective is to investigate the use of cue masking in non-acted emotional speech by analyzing the extent to which filtering impacts the perception of emotional content of the modified speech material. However, obtaining a corpus of emotional speech can be quite difficult whereby verifying the emotional content is an issue thoroughly discussed. Currently, speech research is showing a tendency toward constructing …

Attitudes Of Health Professionals To Electronic Data Sharing Within An Integrated Care Electronic Health Record (Icehr), Charyl O'Malley, Damon Berry, Mary Sharp

Conference Papers

It is estimated that 98,000 people die in hospitals yearly in the USA as a result of medical errors (Agency for Healthcare Research and Quality, 2009). Electronic Health Records (EHR) can offer improved patient safety. EHRs are being implemented by many countries, however, not all health professionals have welcomed them (MORI Social Research Institute, 2006). As outlined in the National Health Information Strategy (NHIS) document, Ireland has plans to introduce an EHR. Attitudes of health professionals are a significant factor for the successful implementation and adoption of a new clinical information system. This study aimed to gauge the attitude of …

Healthcare Professional Roles: The Ontology Model For E-Learning, Lorraine Carmody, Elizabeth Sherry, John Cardiff

Conference Papers

The paper aims to present the MEDeLEARN project, an ontology-driven virtual learning environment for Medical Information System training. The current training environment for healthcare professionals in the use of essential medical information systems in a large urban training hospital is based on conventional instructor-led training sessions. Problems arise due to the demanding nature of the hospital working environment, causing training to be cancelled or curtailed. This mode of training delivery is deemed to be inefficient and ineffective, with the danger of serious errors occurring as a consequence.

The project investigates whether a virtual learning environment can address the competency gap …

Emotional Speech Corpus Construction, Annotation And Distribution, Brian Vaughan, Charlie Cullen, Spyros Kousidis, John Mcauley

Conference papers

This paper details a process of creating an emotional speech corpus by collecting natural emotional speech assets, analysisng and tagging them (for certain acoustic and linguistic features) and annotating them within an on-line database. The definition of specific metadata for use with an emotional speech corpus is crucial, in that poorly (or inaccurately) annotated assets are of little use in analysis. This problem is compounded by the lack of standardisation for speech corpora, particularly in relation to emotion content. The ISLE Metadata Initiative (IMDI) is the only cohesive attempt at corpus metadata standardisation performed thus far. Although not a comprehensive …

Technology-Aided Participative Methods In Environmental Assessment: An International Perspective, Ainhoa Gonzalez, Alan Gilmer, Ronan Foley, John Sweeney, John Fry

Articles

Provisions for citizen involvement in the assessment of potential environmental effects of certain plans, programmes and projects are present in current legislation. An international survey revealed that public participation is common practice in European and some other countries worldwide. However, a number of issues are observed to affect public involvement in EIA/SEA processes and expert opinion differs when evaluating the effectiveness of existing participative methods. Results suggest that technology-aided methods can improve traditional participation processes. In particular, GIS has the potential to increase community knowledge and enhance involvement by communicating information more effectively. Variable accessibility to technology and data quality …