1419 – Language changes as an important psychopathological phenomenon of mild depression

Smirnova, Daria; Sloeva, Elena; Kuvshinova, Natalia; Krasnov, A. N.; Романов, Д. В.; Nosachev, G.

doi:10.1016/s0924-9338(13)76454-x

“…An examination of essays written by depressed, formerly-depressed, and non-depressed college students at University of Texas [17] confirmed an elevated use of the word "I" in particular and also found more negative emotion words in the depressed group. Similarly, a Russian speech study [18] found a more frequent use of all pronouns and verbs in past tense among depression patients. A recent study based on English forum posts [19] observed an elevated use of absolutist words (e.g., absolutely, completely, every, nothing 1 ) within forums related to depression, anxiety, and suicidal ideation than within completely unrelated forums as well as ones about asthma, diabetes, or cancer.…”

Section: Depression and Languagementioning

confidence: 79%

“…The resulting tokens of each message were lowercased (with the exception of emoticons) and separated with a space to enable fastText to properly treat punctuation. 17 Since the dataset also contains messages written in different languages than English and a sophisticated language detection classifier would have required too much time for so many documents, a simple language detection based on stopword counts was utilized: Only messages with more English stopwords than ones from other languages 18 were retained (thus also discarding messages without any stopwords). This resulted in a final training corpus of 1.37 billion messages and a total of 49.9 billion tokens.…”

Section: Word Embeddingsmentioning

confidence: 99%

Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences

Trotzek

¹

,

Koitka

²

,

Friedrich

³

2020

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Depression is ranked as the largest contributor to global disability and is also a major reason for suicide. Still, many individuals suffering from forms of depression are not treated for various reasons. Previous studies have shown that depression also has an effect on language usage and that many depressed individuals use social media platforms or the internet in general to get information or discuss their problems. This paper addresses the early detection of depression using machine learning models based on messages on a social platform. In particular, a convolutional neural network based on different word embeddings is evaluated and compared to a classification based on user-level linguistic metadata. An ensemble of both approaches is shown to achieve state-of-the-art results in a current early detection task. Furthermore, the currently popular ERDE score as metric for early detection systems is examined in detail and its drawbacks in the context of shared tasks are illustrated. A slightly modified metric is proposed and compared to the original score. Finally, a new word embedding was trained on a large corpus of the same domain as the described task and is evaluated as well.

show abstract

“…An examination of essays written by depressed, formerly-depressed, and non-depressed college students at University of Texas [17] confirmed an elevated use of the word "I" in particular and also found more negative emotion words in the depressed group. Similarly, a Russian speech study [18] found a more frequent use of all pronouns and verbs in past tense among depression patients. A recent study based on English forum posts [19] observed an elevated use of absolutist words (e.g.…”

Section: Depression and Languagementioning

confidence: 79%

Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences

Trotzek,

Koitka,

Friedrich

2018

Preprint

View full text Add to dashboard Cite

Depression is ranked as the largest contributor to global disability and is also a major reason for suicide. Still, many individuals suffering from forms of depression are not treated for various reasons. Previous studies have shown that depression also has an effect on language usage and that many depressed individuals use social media platforms or the internet in general to get information or discuss their problems. This paper addresses the early detection of depression using machine learning models based on messages on a social platform. In particular, a convolutional neural network based on different word embeddings is evaluated and compared to a classification based on user-level linguistic metadata. An ensemble of both approaches is shown to achieve state-of-the-art results in a current early detection task. Furthermore, the currently popular ERDE score as metric for early detection systems is examined in detail and its drawbacks in the context of shared tasks are illustrated. A slightly modified metric is proposed and compared to the original score. Finally, a new word embedding was trained on a large corpus of the same domain as the described task and is evaluated as well.

show abstract

Structural and functional markers of language signify the symptomatic effect of depression: A systematic literature review

Savekar

¹

,

Tarai

²

,

Singh

³

2022

European Journal of Applied Linguistics

3

0

View full text Add to dashboard Cite

Human behaviour is encoded and decoded through language. The latter acts as a marker in conceptualising the symptomatic effect of depression and stress. Based on this premise, this study reviewed the results and findings of both qualitative and quantitative research literature on the discourse of depressive patients and which was published between 2010 to 2020. A total of 80 research articles were examined and evaluated for interpretation using the Framework of Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA). Out of these, 25 articles were finalised for analysis and synthesis. The findings on linguistic indicators correlating to depression were interpreted based on (i) prevalent linguistic markers, (ii) the research design, (iii) the significance of the context, and (iv) the limitations of findings across studies that foil establishing the generalizability of linguistic markers. Although function and content words (first-person singular pronouns, negative emotional words) as markers are strongly associated with cognitive symptoms (self-focused attention) of depression, results across studies vary. It is observed that depressive individuals also used the third-person singular (he, she) and plural pronouns (they) while accusing others of referring to negative affect. These findings contribute to the literature on mental health by establishing a correlation between linguistic features and psychological symptoms of depression.

show abstract

1419 – Language changes as an important psychopathological phenomenon of mild depression

Cited by 3 publications

References 0 publications

Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences

Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences

Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences

Structural and functional markers of language signify the symptomatic effect of depression: A systematic literature review

Contact Info

Product

Resources

About