The Decision to Die: The Psychology of the Suicide Note

Gregory, Adam

doi:10.4324/9780429428517-7

Cited by 9 publications

(16 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linguistic features which improved the classification accuracy substantially were the length of a note, number of verbs and nouns as well as the features endearment, and relativity. Gregory (1999) argues that suicide notes are greater in length due to the fact that the author wants to convey as much information as possible, due to their feeling that they will not have time to convey this information at a later point. This proved to be true for the three corpora analysed as the average length of the GSN corpus (144.6 words) was substantially higher than the other two (LH= 70.78 words, DL= 120.85).…”

Section: Discussion Of Linguistic Featuresmentioning

confidence: 99%

“…Finally, we manually annotated the feature 'endearment', which referred to words such as 'Dear' at the beginning of a note or post. Work by Gregory (1999) previously established a significant influence of 'endearment'. Table 1 shows a quantitative comparison of our three corpora showing the number of words of each corpus, number of documents notes, average number of words in each note, clauses in each corpus and average clause length.…”

Section: Sentiment Featuresmentioning

confidence: 99%

“…We can see that while each corpus contained exactly the same number of documents/notes, other statistics such as the number of words or clauses vary substantially across corpora. Previous work by Gregory (1999) can perhaps help shed some light on these differences. Gregory (1999) found that suicide notes are often greater in length due to the fact that the suicidal individual wants to convey as much information as possible.…”

Section: Corpora Statisticsmentioning

confidence: 99%

“…Previous work by Gregory (1999) can perhaps help shed some light on these differences. Gregory (1999) found that suicide notes are often greater in length due to the fact that the suicidal individual wants to convey as much information as possible. This is due to the note writer's feeling that they will not have time to convey this information at a later point (Gregory, 1999).…”

Section: Corpora Statisticsmentioning

confidence: 99%

“…Gregory (1999) found that suicide notes are often greater in length due to the fact that the suicidal individual wants to convey as much information as possible. This is due to the note writer's feeling that they will not have time to convey this information at a later point (Gregory, 1999). In our corpora, we can see this tendency clearly reflected in the overall lengths of notes.…”

Section: Corpora Statisticsmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Identification of Suicide Notes from Linguistic and Sentiment Features

Schoene

Dethlefs

2016

Proceedings of the 10th SIGHUM Workshop on Language Technology For Cultural Heritage, Social Sciences, and Humanities

View full text Add to dashboard Cite

Psychological studies have shown that our state of mind can manifest itself in the linguistic features we use to communicate. Recent statistics in suicide prevention show that young people are increasingly posting their last words online. In this paper, we investigate whether it is possible to automatically identify suicide notes and discern them from other types of online discourse based on analysis of sentiments and linguistic features. Using supervised learning, we show that our model achieves an accuracy of 86.6%, outperforming previous work on a similar task by over 4%.

show abstract

Section: Discussion Of Linguistic Featuresmentioning

confidence: 99%

Section: Sentiment Featuresmentioning

confidence: 99%

Section: Corpora Statisticsmentioning

confidence: 99%

Section: Corpora Statisticsmentioning

confidence: 99%

Section: Corpora Statisticsmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Identification of Suicide Notes from Linguistic and Sentiment Features

Schoene

Dethlefs

2016

Proceedings of the 10th SIGHUM Workshop on Language Technology For Cultural Heritage, Social Sciences, and Humanities

View full text Add to dashboard Cite

show abstract

Automatic identification of suicide notes with a transformer-based deep learning model

Zhang

Schoene

Ananiadou

2021

Internet Interventions

View full text Add to dashboard Cite

Suicide is one of the leading causes of death worldwide. At the same time, the widespread use of social media has led to an increase in people posting their suicide notes online. Therefore, designing a learning model that can aid the detection of suicide notes online is of great importance. However, current methods cannot capture both local and global semantic features. In this paper, we propose a transformer-based model named TransformerRNN, which can effectively extract contextual and long-term dependency information by using a transformer encoder and a Bi-directional Long Short-Term Memory (BiLSTM) structure. We evaluate our model with baseline approaches on a dataset collected from online sources (including 659 suicide notes, 431 last statements, and 2000 neutral posts). Our proposed TransformerRNN achieves 95.0%, 94.9% and 94.9% performance in P, R and F1-score metrics respectively and therefore outperforms comparable machine learning and state-of-the-art deep learning models. The proposed model is effective for classifying suicide notes, which in turn, may help to develop suicide prevention technologies for social media.

show abstract

Exploring the possibility of using appraisal theory to determine the legitimacy of suicide notes

Grundlingh

2018

Lingua

View full text Add to dashboard Cite

The Decision to Die: The Psychology of the Suicide Note

Cited by 9 publications

References 1 publication

Automatic Identification of Suicide Notes from Linguistic and Sentiment Features

Automatic Identification of Suicide Notes from Linguistic and Sentiment Features

Automatic identification of suicide notes with a transformer-based deep learning model

Exploring the possibility of using appraisal theory to determine the legitimacy of suicide notes

Contact Info

Product

Resources

About