Depression detection in social media comments data using machine learning algorithms

Vasha, Zannatun Nayem; Sharma, Bidyut; Esha, Israt Jahan; Nahian, Jabir Al; Polin, Johora Akter

doi:10.11591/eei.v12i2.4182

Cited by 18 publications

(5 citation statements)

References 25 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Research on social media user behavior connected to the onset and amplification of depression and other mental health issues [8][9][10]. 4) Studies on system algorithms and improvements in the underlying system related to emotion, such as the accuracy of different data mining and machine learning algorithms classifiers in detecting emotional data, as illustrated in the latest related study [11]. The research hypothesis adopts a perspective that diverges from conventional research directions, offering a comprehensive and quotidian viewpoint.…”

Section: "Negative Community" and "Negative Emotions"mentioning

confidence: 99%

Prevailing Negative Communities Online: Algorithmic Influence and User Self-awareness

Ma,

Ni,

Yang

2023

LNEP

View full text Add to dashboard Cite

In recent years, the proliferation of short videos imbued with negative sentiment on TikTok has elicited widespread societal attention. This paper investigates the dissemination of negative emotional content on the social media platform TikTok. Specifically, this paper analyzes user data from several short video platforms, including TikTok, and finds that users aged 18-35 constitute the primary audience for short video content. Amid the propagation of negative emotions, this paper proposes the research hypothesis of a negative community. It conducts an in-depth exploration of the following queries: 1) Is the algorithm of TikTok complicit in the spread of negative sentiment? 2) Has this dissemination cultivated unique cultural communication attributes, coalescing into a community-based audience? Moreover, 3) In forming and proliferating negative sentiment, which plays a more significant role the algorithm or the user.

show abstract

Section: "Negative Community" and "Negative Emotions"mentioning

confidence: 99%

Prevailing Negative Communities Online: Algorithmic Influence and User Self-awareness

Ma,

Ni,

Yang

2023

LNEP

View full text Add to dashboard Cite

show abstract

“…In order to provide a more thorough evaluation of a patient's mental state, the authors propose combining this methodology with conventional techniques for detecting depression [8]. Vasha et al [9] used different machine learning algorithms to identify sentiment in social media information, such as Facebook posts and comments. Machine learning algorithms can analyse large amounts of data and generate informative results.…”

Section: Literature Reviewmentioning

confidence: 99%

Depression Identification Using Machine Learning Classifiers

Srivastava,

Pandey,

Gupta

et al. 2023

IJIRCST

View full text Add to dashboard Cite

Depression is a mental condition that indicates emotional issues, including anger issues, unhappiness, boredom, appetite loss, lack of concentration, anxiety, etc. The quality of life of an individual may be negatively impacted by depression, which may ultimately lead to loss of health and life. According to the World Health Organization, there are 300 million depressed persons worldwide in 2022. The number of depression cases rose throughout the pandemic. It became important to detect depression in people accurately. During the construction of the model various machine learning techniques were applied. Support Vector Machine (SVM), Random Forest, Naive Bayes, K Nearest Neighbour (KNN), and Logistic Regression were used to test the accuracy of the model. Among all techniques, Logistic Regression had the highest accuracy. The proposed technique improved the accuracy of 0.79 in comparison with the other existing state of art. Physical health and mental health, both are equally important. Early detection of depression is necessary so that it can be treated in its early stage.

show abstract

“…Feature extraction was based on TF-IDF for the SVM classifiers and Word2vec for LSTM. [53] compared the performances of SVM, KNN, RF, DT, LR and NB on detecting individuals with depression from Facebook and YouTube comments. The retrieved posts were manually annotated as either being depressed or not depressed and feature extraction was based on TF-IDF.…”

Section: Related Workmentioning

confidence: 99%

A Stacking-Based Ensemble Approach with Embeddings from Language Models for Depression Detection from Social Media Text

Gaius,

Mwangi,

Ngunyi

2023

JDAIP

View full text Add to dashboard Cite

Depression is a major public health problem around the world and contributes significantly to poor health and poverty. The rate of the number of people being affected is very high compared to the rate of medical treatment of the disease. Thus, the disease often remains untreated and suffering continues. Machine learning has been widely used in many studies in detecting depressive individuals from their contents on online social networks. From the related reviews, it is apparent that the application of stacking for diagnosing depression has been minimal. The study implements stacking based on Extra Tree, Extreme Gradient Boosting, Light Gradient Boosting and Multi-layer perceptron and compares its performance to state of the art bagging and boosting ensemble learners. To better evaluate the effectiveness of the proposed stacking approach, three pretrain word embeddings techniques including: Word2vec, Global Vectors and Embeddings from language models were employed with two datasets. Also, a corrected resampled paired t-test was applied to test the significance of the stacked accuracy against the baseline accuracy. The experimental results shows that the stacking approach yields favourable results with a best accuracy of 99.54%.

show abstract

Depression detection in social media comments data using machine learning algorithms

Cited by 18 publications

References 25 publications

Prevailing Negative Communities Online: Algorithmic Influence and User Self-awareness

Prevailing Negative Communities Online: Algorithmic Influence and User Self-awareness

Depression Identification Using Machine Learning Classifiers

A Stacking-Based Ensemble Approach with Embeddings from Language Models for Depression Detection from Social Media Text

Contact Info

Product

Resources

About