مطالب

This study aims to explore therapists' experiences with nonverbal communication techniques in psychotherapy for children with autism. This qualitative study employed a phenomenological approach to gain in-depth insights into therapists' experiences. Sixteen licensed therapists with at least two years of experience working with children with autism were selected through purposive sampling. Data were collected through semi-structured interviews, each lasting 60-90 minutes, and were transcribed verbatim for analysis. Thematic analysis was conducted to identify key themes and patterns in the data. NVivo software was used to facilitate the organization and analysis of qualitative data, ensuring rigor through triangulation, member checking, and maintaining an audit trail. The analysis revealed four main themes: implementation of nonverbal techniques, perceived effectiveness, challenges and barriers, and strategies for overcoming barriers. Therapists reported using a variety of nonverbal techniques such as gestures, facial expressions, eye contact, body language, and physical proximity. These techniques were perceived as highly effective in enhancing understanding, emotional connection, behavioral improvements, and self-expression in children with autism. However, challenges such as therapist-child compatibility, resource limitations, environmental factors, and inconsistent parental involvement were noted. Strategies to overcome these challenges included continuous training, collaborative approaches, adaptive techniques, creating supportive environments, and leveraging technology. Nonverbal communication techniques are essential in psychotherapy for children with autism, significantly enhancing therapeutic outcomes. Despite challenges, these techniques, when tailored to individual needs and supported by continuous training and collaboration, can greatly benefit children with autism. Future research should focus on larger and more diverse samples, quantitative measures of effectiveness, and the role of cultural sensitivity in nonverbal communication strategies.

Contemporary machine learning models, like deep neural networks, require substantial labeled datasets for proper training. However, in areas such as natural language processing, a shortage of labeled data can lead to overfitting. To address this challenge, data augmentation, which involves transforming data points to maintain class labels and provide additional valuable information, has become an effective strategy. In this paper, a deep reinforcement learning-based text augmentation method for sentiment analysis was introduced, combining reinforcement learning with deep learning. The technique uses Deep Q-Network (DQN) as the reinforcement learning method to search for an efficient augmentation strategy, employing four text augmentation transformations: random deletion, synonym replacement, random swapping, and random insertion. Additionally, various deep learning networks, including CNN, Bi-LSTM, Transformer, BERT, and XLNet, were evaluated for the training phase. Experimental findings show that the proposed technique can achieve an accuracy of 65.1% with only 20% of the dataset and 69.3% with 40% of the dataset. Furthermore, with just 10% of the dataset, the method yields an F1-score of 62.1%, rising to 69.1% with 40% of the dataset, outperforming previous approaches. Evaluation on the SemEval dataset demonstrates that reinforcement learning can efficiently augment text datasets for improved sentiment analysis results.