Text Comments Research Articles

Classifying Comments in Social Media Networks Using CNN with SVM

People can now communicate with each other and share ideas thanks to social media by posting content on many communication platforms every day. Text comments have become the most widely used in posts across various social media platforms, through which users express their opinions. Manually classifying these comments is a time-consuming process, so this study aims to use artificial intelligence techniques to solve this problem effectively. In this study, we rely on natural language processing (NLP) techniques to classify comments into three categories: positive, negative, and neutral, while using deep learning techniques to increase classification accuracy. The study focuses on classifying tweets posted on the Twitter platform, using a dataset obtained from Kaggle. A long-short-term memory (LSTM) network architecture improved the model performance. The results showed that the proposed model was able to achieve up to 87% accuracy in classifying tweets, highlighting its effectiveness in this field. This model enables reviews to be automatically categorized, which helps customers in their search for goods or services before transacting and saves time. Additionally, marketers can use it to find out what audiences think about their brands and products

Contextual Emotional Transformer-Based Model for Comment Analysis in Mental Health Case Prediction

Mental health (MH) assessment and prediction have become critical areas of focus in healthcare, leveraging developments in natural language processing (NLP). Recent advancements in machine learning have facilitated the exploration of predictive models for MH based on user-generated comments that overlooked the integration of emotional attention mechanisms. The methods often struggle with contextual nuances and emotional subtleties, leading to suboptimal predictions. The prevailing challenge lies in accurately understanding the emotional context embedded within textual comments, which is crucial for effective prediction and intervention. In this research, we introduce a novel approach employing contextual emotional transformer-based models (CETM) for comment analysis in MH case prediction. CETM leverages state-of-the-art transformer architectures enhanced with contextual embedding layers and emotional attention mechanisms for MH case prediction. By incorporating contextual information and emotional cues, CETM captures the underlying emotional states and MH indicators expressed in user comments. Through extensive experimentation and evaluation, both Roberta and bidirectional encoder representations from transformers (BERT) models exhibited enhanced accuracy, precision, recall, and F1 scores compared to their counterparts lacking emotional attention. Notably, the Roberta model attained a greater accuracy of 94.5% when matched to BERT’s 87.6% when emotional attention was employed. Hence, by incorporating emotional context into the predictive model, we achieved significant improvements, which offers promising avenues for more precise and personalized MH interventions.

An online survey of perspectives towards the impact of the covid-19 pandemic amongst caregivers of adolescents with ASD

BackgroundThe coronavirus disease (COVID-19) pandemic has had a negative impact on the health and mental health of adolescents and adolescents with autism spectrum disorders (ASD) and their caregivers, have been disproportionally affected. The purpose of this study was to investigate the impact of COVID-19 on Thai caregivers and adolescents with ASD.MethodsThis study used an online survey with closed and free text questions to investigate how the pandemic had impacted on social skills development and psychological variables, and perceived needs for support. The survey link was shared to parents via the Yuwaprasart Withayopathum Child and Adolescent Hospital and the social media platforms of known ASD stakeholder networks in Thailand. Binary logistic regression was used to investigate the relationships between sociodemographic characteristics, service use, and social skills problems experienced by adolescents during the pandemic. Content analysis was applied to analyse free-text data.ResultsA total of 376 caregivers of adolescents with ASD aged 10–19 years completed the survey, of which 364 were included in the analysis. In total, 38.7% of caregivers reported that during the pandemic the social skills of their adolescent family member had worsened. Most families reported that they were able to continue to access support from healthcare and educational services, albeit in different ways than pre-pandemic, during the acute stages of the pandemic which benefited the maintenance of ASD symptoms and social skills. Factors identified as reducing the odds of a worsening in social skills during the pandemic included; regular access to treatment for adolescents (odds ratio [OR] = 0.55, confidence interval 95% (CI) 0.32–0.98, p = 0.044), caregivers feeling that they had sufficient support from hospitals (OR = 0.46, 95% CI 0.26–0.81, p = 0.007) and older age of adolescents (OR = 0.53, CI 0.29–0.99, p = 0.047). The qualitative free text comments showed that the caregivers felt that greater information on managing adolescent behaviours, opportunities for adolescents to practice social skills, and the provision of greater emotional support and material assistance from healthcare professionals during the pandemic would have helped them to care for the adolescents with ASD.ConclusionRegular access to services, support from hospitals during the pandemic and older age in adolescence may have helped prevent the worsening of the social skills problems of adolescents with ASD.

Menopause Matters: Results of a National Survey of Rheumatoid Arthritis Patients in the UK.

The effects of the menopause have received a lot of attention in the press recently. Anecdotally, patients report changes in their arthritis around the menopause, either onset or aggravation of symptoms. Clearly, there are hormonal influences on arthritis with the female predominance, onset of RA around times of hormonal change and improvement during pregnancy. We were interested in exploring the patient perspective to inform future research and educational needs. A national survey was organised through the National Rheumatoid Arthritis Society (NRAS), using their database of people with RA and online community who self-selected as peri menopausal, menopausal or post-menopausal. A questionnaire was developed by the steering group seeking responses on the effects of the menopause, changes in the arthritis at the time, use of hormone replacement therapy (HRT) and any discussions they had had with their healthcare providers. Free text comments were analysed qualitatively. A total of 779 people responded during September/October 2023. Respondents were 95% Caucasian mainly in their 50s with onset of menopausal symptoms in their 40s. 80% responded that their arthritis was worse during the menopause with 10% being much worse. 47% had taken HRT. Of these, 80% experienced an improvement in their menopausal symptoms and 30% had a moderate or large improvement in their arthritis symptoms. A standout statistic was that 93% of respondents had had no medical discussion about the menopause. For those who did, this was most frequently with the GP in relation to HRT and osteoporosis. 84% of participants felt that the rheumatology team should receive more education and training about the menopause in relation to RA. The qualitative analysis revealed several themes: Discussion about the menopause only occurred if the patient raised it. There was conflicting advice about HRT. There is overlap and confusion of symptoms between RA and the menopause. Participants expressed a perceived link between menopause and onset or deterioration of their arthritis. This study was long overdue. Patients perceive a strong association between the menopause and onset or deterioration of their arthritis, with confusion over what is due to arthritis and what is being caused by the menopause. Patients would like much more discussion about the menopause, but this is not currently happening. They are getting conflicting advice on HRT. Further research is necessary to clarify the impact of the menopause on people with arthritis.

‘More group work would be nice’: exploring peer interaction and belonging in the first-year experiences of culturally and linguistically diverse migrant and refugee students

ABSTRACT A critical factor influencing culturally and linguistically diverse migrant and refugee (CALDMR) students’ educational outcomes is how they experience belonging through peer and educator interactions. To better understand their first-year experiences of belonging, this study analysed 788 responses in the National Student Experience Survey 2020–2022 from first-year CALDMR students studying at a large Australian university. Mixed methods were used with quantitative analysis of closed-ended survey items and qualitative text and thematic analysis of comments relating to peer interaction and sense of belonging. CALDMR students reported lower frequencies of interactions with peers than domestic students with English as first language, yet they highly valued these interactions and believed that educators had a key role in facilitating them. Therefore, this study offers new insights and recommendations on enhancing CALDMR students’ sense of belonging through educator and peer interactions.

Tekstmarkering, kommentarar og metaspråk

How do students in the second year of upper secondary school (vg2) comment on each other’s texts, which text aspects are emphasized and what meta-language do they use in such comments? The article presents a study of first drafts of academic articles in two vg2 classes, where students provide each other with feedback in the form of markings and comments. The texts are part of a text exchange project between two different classes from different parts of the country, where students provide anonymous feedback to the students in the other class. In addition to a classification of the comments with regard to text aspect and the functions of the comments, the specific meta-language the students use is examined more closely. The analysis shows that the students have a good balance between form and content and between micro and macro level in their text comments. At the same time, both praising and directive comments are largely general, which can make them less suitable as a basis for revision. All in all, it seems that the students have stronger and more explicit competence in the overall content and text organization aspects of the texts than is the case for form aspects and language systemic aspects. It is also related to the overall organization of the texts that they to the greatest extent display the use of an expanded meta-language.

Solihull Approach training in undergraduate midwifery education: a pilot study

Background/Aims To date, Solihull training for midwives in Northern Ireland has been facilitated as continuing professional development; however, incorporating Solihull Approach Antenatal Foundation Training in undergraduate midwifery education has been recommended. The aim of this pilot study was to evaluate the provision of this training for undergraduate midwifery students. Methods This mixed-method evaluation study used pre- and post-test questionnaires with a purposive sample of 24 final year midwifery students. The data were analysed using descriptive statistics with thematic analysis of free text comments. Results Four themes emerged: perceived benefits in clinical practice; increased knowledge and confidence; increased recognition of the public health role of the midwife; and integration and timing of the training. Conclusions The innovative initiative was positively evaluated and considered an enhancement to current education provision. However, the initiative would have been welcomed earlier in the education programme. Implications for practice Solihull Approach training will be provided at undergraduate level and introduced earlier in the programme, with the subsequent potential to incrementally build on this foundation and include further tiers of training. The impact of students' application of the Solihull Approach in clinical practice warrants further investigation.

Text Comment Classification and Sentiment Analysis Model Based on LSTM

This study addresses the challenge of sentiment analysis and text classification in user-generated comments, an essential task for understanding public opinion in the digital age. With the widespread adoption of social media, the sheer volume of text data has increased exponentially, thereby necessitating advanced analytical tools. The study integrates Long Short-Term Memory (LSTM) networks with attention mechanisms to develop a model adept at both classifying and analyzing the sentiment of textual comments. The research methodology commences with data cleaning, tokenization, and feature extraction, subsequently followed by the implementation of a bidirectional LSTM architecture augmented with an attention mechanism. The model underwent rigorous training and testing on a comprehensive dataset, yielding high accuracy rates in sentiment analysis and text classification. The results underscore the model’s proficiency in capturing sentiment nuances and underscore its potential for deployment in e-commerce and content recommendation systems, emphasizing the practical implications of this research for enhancing decision-making processes in businesses and among policymakers.

Mental health matters: Evaluating the preparedness of sport psychologists to incorporate within their role.

Mental health has become increasingly important for the applied sport psychologist, a factor which may include screening, promoting literacy, individual support, and educational programs. However, despite of this importance, few checks have been made on the perceived preparedness of sport psychologists to undertake this work and whether differences may exist between those recently qualified compared to experienced practitioners. Underpinned by the theoretical domains framework, 62 Health and Care Professions Council registered practitioner sport and exercise psychologists (30 females: age: M=46.13years and SD=10.44years and 32 males: age: M=43.25years and SD=10.47years) completed an online survey to assess whether they felt equipped to address the mental health dimension of their work. The survey comprised three sections: Demographic and background information, a series of statements (n=31) adapted from the determinants of implementation behavior questionnaire, and three questions with space for free text comments, inviting participants to explain their level of preparedness to incorporate and deliver mental health interventions. A 6×12 analyses of variance yielded significant differences between domain ratings but not across levels of experience or interactions. Data from free text comments were analyzed thematically and categorized into the following three themes: (a) complementing the performance role, (b) awareness of professional boundaries, and (c) importance of further continued professional development. Combined, although practitioners emphasized importance, preparedness ratings ranged from neutral to somewhat agree, calling for further specific sport psychology-based mental health training.

Female Ordination and the Buddha’s Dispensation with a Critical Analysis of <em>Brahmacariya</em> Practice

When the Buddha permitted women to join the monastic community, he predicted that the Buddha’s dispensation (Buddhasāsana) would last only a thousand years due to their ordination. Many scholars dispute this claim. Bhikkhu Anālayo, for example, argues against the Cullavaggapāḷi’s prediction of decline, suggesting it has not materialized, and he explores the impact of the Bhikkhuṇī Order on the dispensation’s longevity. This article investigates how female ordination affects the dispensation and critically analyzes the practice of brahmacariya (celibacy). It utilizes both primary and secondary sources for a thorough critique of existing scholarly views and a detailed examination of brahmacariya within canonical and commentarial texts. The analysis suggests that while female ordination might not cause the complete disappearance of the Buddhasāsana, it could influence the dynamics between monks and nuns, potentially leading to a decline in brahmacariya and spiritual progress within monastic life. Thus, the article supports Bhikkhu Anālayo’s view that the issue lies more with the practice of brahmacariya and spiritual advancement rather than the overall longevity of the dispensation.

Usability and feasibility of an online intervention for older adults to support changes to routines and the home ('Light, activity and sleep in my daily life')

BackgroundIndoor lighting, exposure to outdoor daylight, physical activity and sleep interact to influence functioning, mood and cicadian rhythm. Older adults (≥ 65 years), who often spend more time at home, are less physically active and experience more sleep problems, could benefit from strategies to support behavioural change and self-managed modifications in the home. The study’s primary objective was to assess the usability and feasibility of the ‘Light, activity and sleep in my daily life’ intervention, delivered as a web-based course.MethodsThis 9-week intervention was delivered in a municipality in Sweden (55.70° N). Participants were eight healthy women (age 71–84), community-living in one-person households. We recruited through municipal staff and posters at senior citizen meeting points. Both qualitative and quantitative data were collected before and after the intervention. The outcome measures were intervention usability (ease of use, usefulness) and study feasibility (e.g., recruitment procedure, online engagement). Measures also included changes to routines and self-managed home adjustments to determine whether the participants applied what they had learnt.ResultsAll participants completed the intervention. Time logged in varied between 25 min and 3 h (M = 1 h 50 min) per week. Seven participants’ system usability scores were between 90 and 100 (‘Excellent’) out of 100. When interviewed, participants reported overall high satisfaction with what they had learnt. Six participants were particularly satisfied with the modules targeting light. Seven participants made changes to their lighting or darkness conditions, such as replaced bulbs with either 3-step dimming or higher colour temperature LEDs (samples were included in the intervention test kit). One suggestion to improve the online delivery was to enable participants to add text comments to the weekly evaluation form.ConclusionsThe web-based intervention was feasible to deliver but time for recruitment should be extended and advertisement in the local newspaper should be considered. Participants’ computer proficiency and access to the internet at home will be critical in a future study with a larger sample. Only minor changes to the online content of the intervention are needed based on participants’ feedback. The intervention will be possible to evaluate in a future pilot study.

Recognizing Implicitly Toxic Content Based on Multiple Attention Mechanisms

ABSTRACTToxic content on social media has posed a significant threat to user experience and societal stability. In contrast to explicitly toxic content, implicitly toxic content, lacking overt toxic words, is challenging to identify through single‐text features. Therefore, this study proposes a multi‐feature fusion algorithm to recognize implicit toxic content. Firstly, we collect various features for each post, including text content, likes, comments, user information and other features. Subsequently, employing a multi‐head attention mechanism, we extract and fuse these features. Then, utilizing ensemble learning algorithms, we identify implicitly toxic content based on the fused features. Finally, we analyze the decision‐making process of the model using an interpretable algorithm and derive the most critical features and factors for identifying implicitly toxic content. The experimental results show that the proposed algorithm outperforms algorithms such as BERT, TextCNN, and XGBoost, demonstrating the advantage of multiple features over a single text feature in recognizing implicitly toxic content. In addition, this study provides insights into the decision‐making process of the model and provides more effective toxic content management strategies for social media platforms.

"I Had No Idea This Happened": Electronic Feedback on Clinical Reasoning for Hospitalists.

Feedback on the diagnostic process has been proposed as a method of improving clinical reasoning and reducing diagnostic errors. Barriers to the delivery and receipt of feedback include time constraints and negative reactions. Given the shift toward asynchronous, digital communication, it is possible that electronic feedback ("e-feedback") could overcome these barriers. We developed an e-feedback system for hospitalists around episodes of care escalation (transfers to ICU and rapid responses). The intervention was evaluated by measuring hospitalists' satisfaction with e-feedback and commitment to change. A qualitative survey study conducted at one academic medical center from February to June 2023. Hospitalists - physicians and advanced practice providers. Two hospitalists, one internal medicine resident, and a nurse reviewed escalations of care on the hospitalist service each week using the Revised Safer Dx framework. Confidential feedback was emailed to the hospitalists involved in the patient's care. Hospitalists were asked to rate and explain their satisfaction with the e-feedback and whether they might modify their clinical practice based on the e-feedback. The open-ended text comments from the hospitalists were analyzed using a thematic analysis framework. Forty-nine out of fifty-eight hospitalists agreed to participate. One hundred five out of one hundred twenty-four (85%) e-feedback surveys that were sent were returned by the hospitalists. Hospitalists were highly satisfied with 67% (n = 70) of the e-feedback reports, moderately satisfied with 23% (n = 24), and not satisfied with 10% (n = 11). Six themes were identified based on analysis of the comments. Themes related to satisfaction with the intervention included appreciation for learning about patient outcomes, general appreciation of feedback on clinical care, and importance of detailed and specific feedback. Themes related to changing clinical practice included reflection on clinical decision-making, value of new insights, and anticipated future behavior change. E-feedback was well received by hospitalists. Their perspectives offer useful insights for enhancing electronic feedback interventions.

Patient Experience in Older Adults Ambulatory Care services in a large Irish teaching hospital

Abstract Background Ambulatory care pathways aim to reduce hospital overcrowding, provide multidisciplinary, speciality outpatient care, in a timely and cost-effective manner to older people with complex care needs. The delivery of care is centred on the needs of the patient; obtaining and implementing personalized feedback is essential to upholding the highest standards of care. Methods All Patients attending ambulatory care services, at a large teaching hospital in 2023–2024 were offered a 30-question survey covering demographics, hospital access, facility usage, and care delivery, with yes/no responses, 5-point Likert scale and free text comments. Results This cohort represents 3.5% of overall service users (n=642). Of the group in question, 55% were between 65 and 85, and 10% were over 85, a quarter were under 65. A quarter of people were seen within a month, a further 38% within four months of referral. 63% of respondents travelled by car, 31% took public transportation, 5% walked, and 1% rode a bike. 68% of older adults commuted by car (12% by taxi). Taxi use was due to inability to conveniently access onsite parking. Over three quarters were accompanied to their appointment. A delay was reported by 24% of respondents, two thirds cited a parking issue on campus, with almost 20% identifying a traffic issue. 4% found the distance from the car park to the department challenging. The majority of concerns related to campus traffic and delays getting parking onsite. When asked to rate communication, the environment, and multidisciplinary care delivery, 99%-100% responded positively. Conclusion Care delivery was positively represented in this sample. This patient feedback highlights the need for accessible parking in hospital infrastructure planning. Vulnerable older adults requiring supportive care should be protected from the cost implications of hospital attendance, costly taxi use is indicated in this group. There is a need for national action on this.

A Comparative Analysis of the Water Odes by Sururi and Fuzuli, and the Commentary on Sururi’s Water Ode

In our classical literature, all the poems of Fuzuli in the genres of ghazal, qasida, and masnavi have influenced subsequent poets in terms of their literary value. The Water Ode, due to the excellence in its subject matter and its treatment, has been imitated by poets who came after Fuzuli. Sururi, by composing his own Water Ode, proclaimed his presence in this field. However, Sururi's Water Ode is not as successful as that of Fuzuli. Renowned as a commentator on masnavi and known for his annotations on Sheikh Saadi Shirazi's works "Bostan" and "Gulistan," Sururi is one of the significant figures who shed light on his era. This article first provides information on text commentary and the theories proposed in this context. A comparison of the Water Odes by Fuzuli and Sururi will be made, and the commentary on Sururi’s Water Ode will be examined. Keywords: Sururi, life, art, works, Fuzuli’s Water Ode, Sururi’s Water Ode, text commentary.

Quantifying the relationship between US residential mobility and fire service call volume

PurposeThe COVID-19 pandemic dramatically affected the fire service: stay-at-home orders and potential exposure hazards disrupted standard fire service operations and incident patterns. The ability to predict incident volume during such disruptions is crucial for dynamic and efficient staff allocation planning. This work proposes a model to quantify the relationship between the increase in “residential mobility” (i.e. time spent at home) due to COVID-19 and fire and emergency medical services (EMS) call volume at the onset of the pandemic (February – May 2020). Understanding this relationship is beneficial should mobility disruptions of this scale occur again.Design/methodology/approachThe analysis was run on 56 fire departments that subscribe to the National Fire Operations Reporting System (NFORS). This platform enables fire departments to report and visualize operational data. The model consists of a Bayesian hierarchical model. Text comments reported by first responders were also analyzed to provide additional context for the types of incidents that drive the model’s results.FindingsOverall, a 1% increase in residential mobility (i.e. time spent at home) was associated with a 1.43% and 0.46% drop in EMS and fire call volume, respectively. Around 89% and 21% of departments had a significant decrease in EMS and fire call volume, respectively, as time spent at home increased.Originality/valueA few papers have investigated the impact of COVID-19 on fire incidents in a few locations, but none have covered an extensive number of fire departments. Additionally, no studies have investigated the relationship between mobility and fire department call volumes.

Using Patient Experience Surveys to Identify Potential Diagnostic Safety Breakdowns: A Mixed Methods Study.

One in 20 outpatients in the United States experiences a diagnostic error each year, but there are no validated methods for collecting feedback from patients on diagnostic safety. We examined patient experience surveys to determine whether patients' free text comments indicated diagnostic breakdowns. Our objective was to evaluate associations between patient-perceived diagnostic breakdowns reported in free text comments and patients' responses to structured survey questions. We conducted an exploratory mixed methods study using data from patient experience surveys collected from adult ambulatory care patients March 2020 to June 2020 in a large U.S. health system. Data analysis included content analysis of qualitative data and statistical analysis of quantitative data. In 2525 surveys with negative comments, 619 patients (24.5%) identified diagnostic breakdowns, including issues with accuracy (n = 282, 46%), timeliness (n = 243, 39%), or communication (n = 290, 47%); some patients (n = 181) reported breakdowns in multiple categories. Patients who gave a low average score (50 or less on a 100-point scale) on provider questions were almost seven times more likely to perceive a diagnostic breakdown than patients who scored their provider higher. Similarly, patients who gave a low average score on practice-related questions were twice as likely to perceive a diagnostic breakdown. Patient feedback in routinely collected patient experience surveys is a valuable and actionable information source on diagnostic breakdowns in the ambulatory setting. The more easily monitored structured survey data provide a screening method to identify encounters that may have included a patient-perceived diagnostic breakdown and therefore require further examination.

Midwifery student engagement with digital interactive books: A cross sectional survey

AimTo explore the benefit and engagement of undergraduate students’ use of H5P interactive books for student learning. DesignAn evaluation study of technology enabled learning for first year undergraduate Bachelor of Midwifery students in Australia. MethodsStudents were invited to complete an online evaluation survey of their use and engagement with H5P interactive books. The survey included the long form User Engagement Scale which has four subscales of focused attention, aesthetic appeal, reward factor and perceived usability scored on a 5-point Likert scale. Content analysis was used to analyse the text comments given to five open text questions. ResultsThere were 21 students who completed the survey. There was a high overall User Engagement Scale score of 73.1 % with aesthetic appeal and reward factor being the highest scoring subscales. The content analysis showed students found the interactive books engaging and easy to navigate. Areas for improvement identified were not including a large amount of content and providing downloadable content. ConclusionsThis study demonstrates the valuable and engaging use of H5P Interactive Books for undergraduate students in higher education. Students who used H5P Interactive Books identified their ease of use, organised layout and engaging format.

Discursive Patinas: Anchoring Discussions in Data Visualizations.

This paper presents discursive patinas, a technique to visualize discussions onto data visualizations, inspired by how people leave traces in the physical world. While data visualizations are widely discussed in online communities and social media, comments tend to be displayed separately from the visualization and we lack ways to relate these discussions back to the content of the visualization, e.g., to situate comments, explain visual patterns, or question assumptions. In our visualization annotation interface, users can designate areas within the visualization. Discursive patinas are made of overlaid visual marks (anchors), attached to textual comments with category labels, likes, and replies. By coloring and styling the anchors, a meta visualization emerges, showing what and where people comment and annotate the visualization. These patinas show regions of heavy discussions, recent commenting activity, and the distribution of questions, suggestions, or personal stories. We ran workshops with 90 students, domain experts, and visualization researchers to study how people use anchors to discuss visualizations and how patinas influence people's understanding of the discussion. Our results show that discursive patinas improve the ability to navigate discussions and guide people to comments that help understand, contextualize, or scrutinize the visualization. We discuss the potential of anchors and patinas to support discursive engagements, including critical readings of visualizations, design feedback, and feminist approaches to data visualization.

Evolution of radiology staff perspectives during artificial intelligence (AI) implementation for expedited lung cancer triage

To investigate radiology staff perceptions of an AI tool for chest radiography triage, flagging findings suspicious for lung cancer to expedite same-day CT chest examination studies. Surveys were distributed to all radiology staff at three time points: at pre-implementation, one month and also seven months post-implementation of artificial intelligence (AI). Survey questions captured feedback on AI use and patient impact. Survey response rates at the three time periods were 23.1% (45/195), 14.9% (29/195) and 27.2% (53/195), respectively. Most respondents initially anticipated AI to be time-saving for the department and patient (50.8%), but this shifted to faster follow-up care for patients after AI implementation (51.7%). From the free text comments, early apprehension about job role changes evolved into frustration regarding technical integration challenges after implementation. This later transitioned to a more balanced view of recognised patient benefits versus minor ongoing logistical issues by the late post-implementation stage. There was majority disagreement across all survey periods that AI could be considered to be used autonomously (53.3-72.5%), yet acceptance grew for personal AI usage if staff were to be patients themselves (from 31.1% pre-implementation to 47.2% post-implementation). Successful AI integration in radiology demands active staff engagement, addressing concerns to transform initial mixed excitement and resistance into constructive adaptation. Continual feedback is vital for refining AI deployment strategies, ensuring its beneficial and sustainable incorporation into clinical care pathways.