Indirect Identification of Perinatal Psychosocial Risks From Natural Language

Allen, Kristen; Davis, Alexander; Krishnamurti, Tamar

doi:10.1109/taffc.2021.3079282

Cited by 8 publications

(11 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The N = 22 included studies cover a wide range of research questions and text mining methodologies. Outcomes include extracting topics from a corpus of social media texts (More & Francis, 2021;Rodriguez & Storer, 2020;Xue, Chen, Chen, Hu, & Zhu, 2020;Xue et al, 2019), information retrieval of abuse and injury types from police reports (Adily et al, 2021), detecting the presence or absence of mentions of domestic violence in various types of text (Allen, Davis, & Krishnamurti, 2021;Botelle et al, 2022;Victor et al, 2021), and event and entity recognition from court documents (Li, Sheng, Ge, & Luo, 2019) and victim-survivor narratives (Liu, Li, Liu, Zhang, & Si, 2019). A summary of the studies can be found in Table 1.…”

Section: Included Studiesmentioning

confidence: 99%

“…Sanchez-Moya (2017) used Linguistic Inquiry and Word Count (LIWC) (Pennebaker, Francis, & Booth, 2001), a computational tool for linguistic analysis. This technique was also used in four other studies as an addition, or an input into, more complex models (Allen et al, 2021;Rodriguez & Storer, 2020;S Subramani et al, 2018aS Subramani et al, , 2018b. LIWC is a dictionary-based method, in that it counts the number of words in a text which belong to a series of dictionaries of words from particular linguistic categories (e.g.…”

Section: Unsupervised Exploratory Approachesmentioning

confidence: 99%

“…The size of the datasets varies considerably, from 309 diary entries (Allen et al, 2021) to over 1 million unique Tweets (Xue et al, 2020). The size of each text within a dataset also varies, from a single Tweet (Homan et al, 2020) to entire litigation texts or case summaries (Victor et al, 2021).…”

Section: Sizementioning

confidence: 99%

“…Most datasets were labelled by supervised student reviewers. However, some datasets took advantage of existing properties of the data to create labels -for example, by using hashtags applied to tweets (Homan et al, 2020), participant surveys administered alongside the collection of text data (Allen et al, 2021), or police assigned labels collected during the incident reporting process (J Poelmans, Van Hulle, et al, 2011). Such techniques can significantly reduce the time and cost burden for researchers and show the benefit of trying to find label-type properties within existing data.…”

Section: Labelling Processmentioning

confidence: 99%

See 3 more Smart Citations

A Systematic Literature Review of the Use of Computational Text Analysis Methods in Intimate Partner Violence Research

et al. 2023

View full text Add to dashboard Cite

Purpose Computational text mining methods are proposed as a useful methodological innovation in Intimate Partner Violence (IPV) research. Text mining can offer researchers access to existing or new datasets, sourced from social media or from IPV-related organisations, that would be too large to analyse manually. This article aims to give an overview of current work applying text mining methodologies in the study of IPV, as a starting point for researchers wanting to use such methods in their own work. Methods This article reports the results of a systematic review of academic research using computational text mining to research IPV. A review protocol was developed according to PRISMA guidelines, and a literature search of 8 databases was conducted, identifying 22 unique studies that were included in the review. Results The included studies cover a wide range of methodologies and outcomes. Supervised and unsupervised approaches are represented, including rule-based classification (n = 3), traditional Machine Learning (n = 8), Deep Learning (n = 6) and topic modelling (n = 4) methods. Datasets are mostly sourced from social media (n = 15), with other data being sourced from police forces (n = 3), health or social care providers (n = 3), or litigation texts (n = 1). Evaluation methods mostly used a held-out, labelled test set, or k-fold Cross Validation, with Accuracy and F1 metrics reported. Only a few studies commented on the ethics of computational IPV research. Conclusions Text mining methodologies offer promising data collection and analysis techniques for IPV research. Future work in this space must consider ethical implications of computational approaches.

show abstract

Section: Included Studiesmentioning

confidence: 99%

Section: Unsupervised Exploratory Approachesmentioning

confidence: 99%

Section: Sizementioning

confidence: 99%

Section: Labelling Processmentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Literature Review of the Use of Computational Text Analysis Methods in Intimate Partner Violence Research

et al. 2023

View full text Add to dashboard Cite

show abstract

“… 15 – 17 Few have focused on language as it relates to maternal depression. 18 – 20 We further this prior work in two ways. First, we elicit journaling language from our population of interest by embedding open-ended text opportunities in prenatal care mobile health app.…”

Section: Introductionmentioning

confidence: 99%