FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220928686> ?p ?o ?g. }

• W4220928686 abstract "Abstract Depressed individuals use language differently than healthy controls and it has been proposed that social media posts can be used to identify depression. Much of the evidence behind this claim relies on indirect measures of mental health and few studies have tested if these language features are specific to depression versus other aspects of mental health. We analysed the Tweets of 1006 participants who completed questionnaires assessing symptoms of depression and 8 other mental health conditions. Daily Tweets were subjected to textual analysis and the resulting linguistic features were used to train an Elastic Net model on depression severity, using nested cross-validation. We then tested performance in a held-out test set (30%), comparing predictions of depression versus 8 other aspects of mental health. The depression trained model had modest out-of-sample predictive performance, explaining 2.5% of variance in depression symptoms ( R 2 = 0.025, r = 0.16). The performance of this model was as-good or superior when used to identify other aspects of mental health: schizotypy, social anxiety, eating disorders, generalised anxiety, above chance for obsessive-compulsive disorder, apathy, but not significant for alcohol abuse or impulsivity. Machine learning analysis of social media data, when trained on well-validated clinical instruments, could not make meaningful individualised predictions regarding users’ mental health. Furthermore, language use associated with depression was non-specific, having similar performance in predicting other mental health problems." @default.
• W4220928686 created "2022-04-03" @default.
• W4220928686 creator A5030887892 @default.
• W4220928686 creator A5040846702 @default.
• W4220928686 creator A5050499058 @default.
• W4220928686 creator A5081815613 @default.
• W4220928686 creator A5084096141 @default.
• W4220928686 date "2022-03-25" @default.
• W4220928686 modified "2023-10-18" @default.
• W4220928686 title "Machine learning of language use on Twitter reveals weak and non-specific predictions" @default.
• W4220928686 cites W1632327998 @default.
• W4220928686 cites W1977465442 @default.
• W4220928686 cites W1982921548 @default.
• W4220928686 cites W2025733776 @default.
• W4220928686 cites W2043046773 @default.
• W4220928686 cites W2049017883 @default.
• W4220928686 cites W2053455808 @default.
• W4220928686 cites W2054515032 @default.
• W4220928686 cites W2058971120 @default.
• W4220928686 cites W2072675130 @default.
• W4220928686 cites W2080947232 @default.
• W4220928686 cites W2081249542 @default.
• W4220928686 cites W2083388787 @default.
• W4220928686 cites W2085465737 @default.
• W4220928686 cites W2087822915 @default.
• W4220928686 cites W2089670717 @default.
• W4220928686 cites W2089683052 @default.
• W4220928686 cites W2093106172 @default.
• W4220928686 cites W2094553285 @default.
• W4220928686 cites W2106686523 @default.
• W4220928686 cites W2110608362 @default.
• W4220928686 cites W2120379285 @default.
• W4220928686 cites W2122825543 @default.
• W4220928686 cites W2154887492 @default.
• W4220928686 cites W2159923678 @default.
• W4220928686 cites W2168157616 @default.
• W4220928686 cites W2170332928 @default.
• W4220928686 cites W2170684975 @default.
• W4220928686 cites W2214459822 @default.
• W4220928686 cites W2250553926 @default.
• W4220928686 cites W2251383488 @default.
• W4220928686 cites W2252128283 @default.
• W4220928686 cites W2252191003 @default.
• W4220928686 cites W2288341381 @default.
• W4220928686 cites W2291227510 @default.
• W4220928686 cites W2395932383 @default.
• W4220928686 cites W2402700 @default.
• W4220928686 cites W2405042511 @default.
• W4220928686 cites W2464870181 @default.
• W4220928686 cites W2467392510 @default.
• W4220928686 cites W2508051475 @default.
• W4220928686 cites W2513928994 @default.
• W4220928686 cites W2587676558 @default.
• W4220928686 cites W2593668264 @default.
• W4220928686 cites W2596823239 @default.
• W4220928686 cites W2620859857 @default.
• W4220928686 cites W2729540173 @default.
• W4220928686 cites W2741216199 @default.
• W4220928686 cites W2741613565 @default.
• W4220928686 cites W2748635631 @default.
• W4220928686 cites W2773170638 @default.
• W4220928686 cites W2783564726 @default.
• W4220928686 cites W2793785670 @default.
• W4220928686 cites W2795715081 @default.
• W4220928686 cites W2795781768 @default.
• W4220928686 cites W2798684758 @default.
• W4220928686 cites W2803692240 @default.
• W4220928686 cites W2806490500 @default.
• W4220928686 cites W2806567743 @default.
• W4220928686 cites W2809979304 @default.
• W4220928686 cites W2885386535 @default.
• W4220928686 cites W2886709905 @default.
• W4220928686 cites W2889391310 @default.
• W4220928686 cites W2894724491 @default.
• W4220928686 cites W2897583329 @default.
• W4220928686 cites W2901843597 @default.
• W4220928686 cites W2908543495 @default.
• W4220928686 cites W2932216334 @default.
• W4220928686 cites W2948537574 @default.
• W4220928686 cites W2955382130 @default.
• W4220928686 cites W2962848499 @default.
• W4220928686 cites W2963702943 @default.
• W4220928686 cites W2969758504 @default.
• W4220928686 cites W3008434086 @default.
• W4220928686 cites W3013908145 @default.
• W4220928686 cites W3049771035 @default.
• W4220928686 cites W3081365410 @default.
• W4220928686 cites W3126099275 @default.
• W4220928686 cites W3160351348 @default.
• W4220928686 cites W4213318332 @default.
• W4220928686 cites W4312478474 @default.
• W4220928686 cites W48895825 @default.
• W4220928686 doi "https://doi.org/10.1038/s41746-022-00576-y" @default.
• W4220928686 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35338248" @default.
• W4220928686 hasPublicationYear "2022" @default.
• W4220928686 type Work @default.
• W4220928686 citedByCount "5" @default.
• W4220928686 countsByYear W42209286862022 @default.
• W4220928686 countsByYear W42209286862023 @default.
• W4220928686 crossrefType "journal-article" @default.

• next