Showing items 1 - 7 of 7

Your selections:

Machine learning in mental health: a scoping review of methods and applications

- Shatte, Adrian, Hutchinson, Delyse, Teague, Samantha

  • Authors: Shatte, Adrian , Hutchinson, Delyse , Teague, Samantha
  • Date: 2019
  • Type: Text , Journal article
  • Relation: Psychological Medicine Vol. 49, no. 9 (2019), p. 1426-1448
  • Full Text: false
  • Reviewed:
  • Description: This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice. We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review. Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis (ii) prognosis, treatment and support (iii) public health, and (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering. Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Sequence-to-sequence learning-based conversion of pseudo-code to source code using neural translation approach

- Acharjee, Uzzal, Arefin, Minhazul, Hossen, Kazi, Uddin, Mohammed, Uddin, Md Ashraf, Islam, Linta

  • Authors: Acharjee, Uzzal , Arefin, Minhazul , Hossen, Kazi , Uddin, Mohammed , Uddin, Md Ashraf , Islam, Linta
  • Date: 2022
  • Type: Text , Journal article
  • Relation: IEEE Access Vol. 10, no. (2022), p. 26730-26742
  • Full Text:
  • Reviewed:
  • Description: Pseudo-code refers to an informal means of representing algorithms that do not require the exact syntax of a computer programming language. Pseudo-code helps developers and researchers represent their algorithms using human-readable language. Generally, researchers can convert the pseudo-code into computer source code using different conversion techniques. The efficiency of such conversion methods is measured based on the converted algorithm's correctness. Researchers have already explored diverse technologies to devise conversion methods with higher accuracy. This paper proposes a novel pseudo-code conversion learning method that includes natural language processing-based text preprocessing and a sequence-to-sequence deep learning-based model trained with the SPoC dataset. We conducted an extensive experiment on our designed algorithm using descriptive bilingual understudy scoring and compared our results with state-of-the-art techniques. Result analysis shows that our approach is more accurate and efficient than other existing conversion methods in terms of several performances metrics. Furthermore, the proposed method outperforms the existing approaches because our method utilizes two Long-Short-Term-Memory networks that might increase the accuracy. © 2013 IEEE.

Cyberbullying detection on social networks using machine learning approaches

- Islam, Md Manowarul, Uddin, Md Ashraf, Islam, Linta, Akter, Arnisha, Sharmin, Selina, Acharjee, Uzzal

  • Authors: Islam, Md Manowarul , Uddin, Md Ashraf , Islam, Linta , Akter, Arnisha , Sharmin, Selina , Acharjee, Uzzal
  • Date: 2020
  • Type: Text , Conference paper
  • Relation: 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2020
  • Full Text: false
  • Reviewed:
  • Description: The use of social media has grown exponentially over time with the growth of the Internet and has become the most influential networking platform in the 21st century. However, the enhancement of social connectivity often creates negative impacts on society that contribute to a couple of bad phenomena such as online abuse, harassment cyberbullying, cybercrime and online trolling. Cyberbullying frequently leads to serious mental and physical distress, particularly for women and children, and even sometimes force them to attempt suicide. Online harassment attracts attention due to its strong negative social impact. Many incidents have recently occurred worldwide due to online harassment, such as sharing private chats, rumours, and sexual remarks. Therefore, the identification of bullying text or message on social media has gained a growing amount of attention among researchers. The purpose of this research is to design and develop an effective technique to detect online abusive and bullying messages by merging natural language processing and machine learning. Two distinct freatures, namely Bag-of Words (BoW) and term frequency-inverse text frequency (TFIDF), are used to analyse the accuracy level of four distinct machine learning algorithms. © 2020 IEEE.

Multi-aspect annotation and analysis of Nepali tweets on anti-establishment election discourse

- Rauniyar, Kritesh, Poudel, Sweta, Shiwakoti, Shuvam, Thapa, Surendrabikram, Rashid, Junaid, Kim, Jungeun, Imran, Muhammad, Naseem, Usman

  • Authors: Rauniyar, Kritesh , Poudel, Sweta , Shiwakoti, Shuvam , Thapa, Surendrabikram , Rashid, Junaid , Kim, Jungeun , Imran, Muhammad , Naseem, Usman
  • Date: 2023
  • Type: Text , Journal article
  • Relation: IEEE Access Vol. 11, no. (2023), p. 143092-143115
  • Full Text:
  • Reviewed:
  • Description: In today's social media-dominated landscape, digital platforms wield substantial influence over public opinion, particularly during crucial political events such as electoral processes. These platforms become hubs for diverse discussions, encompassing topics, reforms, and desired changes. Notably, in times of government dissatisfaction, they serve as arenas for anti-establishment discourse, highlighting the need to analyze public sentiment in these conversations. However, the analysis of such discourse is notably scarce, even in high-resource languages, and entirely non-existent in the context of the Nepali language. To address this critical gap, we present Nepal Anti Establishment discourse Tweets (NAET), a novel dataset comprising 4,445 multi-aspect annotated Nepali tweets, facilitating a comprehensive understanding of political conversations. Our contributions encompass evaluating tweet relevance, sentiment, and satire, while also exploring the presence of hate speech, identifying its targets, and distinguishing directed and non-directed expressions. Additionally, we investigate hope speech, an underexplored aspect crucial in the context of anti-establishment discourse, as it reflects the aspirations and expectations from new political figures and parties. Furthermore, we set NLP-based baselines for all these tasks. To ensure a holistic analysis, we also employ topic modeling, a powerful technique that helps us identify and understand the prevalent themes and patterns emerging from the discourse. Our research thus presents a comprehensive and multi-faceted perspective on anti-establishment election discourse in a low-resource language setting. The dataset is publicly available, facilitating in-depth analysis of political tweets in Nepali discourse and further advancing NLP research for the Nepali language through labeled data and baselines for various NLP tasks. The dataset for this work is made available at https://github.com/rkritesh210/NAET. © 2013 IEEE.

Using psycholinguistic features for profiling first language of authors

- Torney, Rosemary, Vamplew, Peter, Yearwood, John

  • Authors: Torney, Rosemary , Vamplew, Peter , Yearwood, John
  • Date: 2012
  • Type: Text , Journal article
  • Relation: Journal of the American Society for Information Science and Technology Vol. 63, no. 6 (2012), p. 1256-1269
  • Full Text: false
  • Reviewed:
  • Description: This study empirically evaluates the effectiveness of different feature types for the classification of the first language of an author. In particular, it examines the utility of psycholinguistic features, extracted by the Linguistic Inquiry and Word Count (LIWC) tool, that have not previously been applied to the task of author profiling. As LIWC is a tool that has been developed in the psycholinguistic field rather than the computational linguistics field, it was hypothesized that it would be effective, both as a single type feature set because of its psycholinguistic basis, and in combination with other feature sets, because it should be sufficiently different to add insight rather than redundancy. It was found that LIWC features were competitive with previously used feature types in identifying the first language of an author, and that combined feature sets including LIWC features consistently showed better accuracy rates and average F measures than were achieved by the same feature sets without the LIWC features. As a secondary issue, this study also examined how effectively first language classification scaled up to a larger number of possible languages. It was found that the classification scheme scaled up effectively to the entire 16 language collection from the International Corpus of Learner English, when compared with results achieved on just 5 languages in previous research. 2012 ASIS&T.

A multilevel description of textbook linguistic complexity across disciplines: Leveraging NLP to support disciplinary literacy

- Green, Clarence

  • Authors: Green, Clarence
  • Date: 2019
  • Type: Text , Journal article
  • Relation: Linguistics and education Vol. 53, no. (2019), p. 100748
  • Full Text: false
  • Reviewed:
  • Description: •Linguistic complexity measured at the clause, phrase and lexical levels, in textbooks from eight secondary school subjects•Innovative natural language processing systems extract an unprecedented number of complexity measures.•Limited studies have been done on the differing linguistic complexity demands of disciplines.•Discriminant function analysis is employed to describe features that best differentiate disciplinary writing.•Paper concludes with detailed and specific pedagogical takeaways for teachers. Disciplinary Literacy as a pedagogy and research program aims to understand and teach the linguistic differences amongst disciplines. Limited studies have been done, however, on the differing linguistic complexity demands of disciplines. In this study, linguistic complexity is measured at the clause, phrase and lexical levels, across eight disciplines represented by a corpus of secondary school textbooks. Innovative natural language processing systems extract an unprecedented number of complexity measures, and discriminant function analysis describes features that best differentiate disciplinary writing. Results indicate disciplines vary along different clines of complexity. The first tends to discriminate humanities from science subjects, along features such as academic phraseology, possessive noun phrases, auxiliary verbs and clause dependents. Other clines show that subjects such as history and physics can be similarly complex in features such as their prepositional expansion of noun phrases. The paper concludes with detailed and specific pedagogical takeaways for teachers.

Graph self-supervised learning : a survey

- Liu, Yixin, Jin, Ming, Pan, Shirui, Zhou, Chuan, Zheng, Yu, Xia, Feng, Yu, Philip

  • Authors: Liu, Yixin , Jin, Ming , Pan, Shirui , Zhou, Chuan , Zheng, Yu , Xia, Feng , Yu, Philip
  • Date: 2023
  • Type: Text , Journal article
  • Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 6 (2022), p. 5879-5900
  • Full Text:
  • Reviewed:
  • Description: Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. IEEE
  • 1