Big Data and Dysmenorrhea: What Questions Do Women and Men Ask about Menstrual Pain?

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: Menstrual pain is highly prevalent among women of reproductive age. As the general public increasingly obtains health information online, Big Data from online platforms provide novel sources to understand the public's perspectives and information needs about menstrual pain. The study's purpose was to describe salient queries about dysmenorrhea using Big Data from a question and answer platform. Materials and Methods: We performed text-mining of 1.9 billion queries from ChaCha, a United States-based question and answer platform. Dysmenorrhea-related queries were identified by using keyword searching. Each relevant query was split into token words (i.e., meaningful words or phrases) and stop words (i.e., not meaningful functional words). Word Adjacency Graph (WAG) modeling was used to detect clusters of queries and visualize the range of dysmenorrhea-related topics. We constructed two WAG models respectively from queries by women of reproductive age and bymen. Salient themes were identified through inspecting clusters of WAG models. Results: We identified two subsets of queries: Subset 1 contained 507,327 queries from women aged 13-50 years. Subset 2 contained 113,888 queries from men aged 13 or above. WAG modeling revealed topic clusters for each subset. Between female and male subsets, topic clusters overlapped on dysmenorrhea symptoms and management. Among female queries, there were distinctive topics on approaching menstrual pain at school and menstrual pain-related conditions; while among male queries, there was a distinctive cluster of queries on menstrual pain from male's perspectives. Conclusions: Big Data mining of the ChaCha® question and answer service revealed a series of information needs among women and men on menstrual pain. Findings may be useful in structuring the content and informing the delivery platform for educational interventions.

Original languageEnglish (US)
Pages (from-to)1233-1241
Number of pages9
JournalJournal of Women's Health
Volume27
Issue number10
DOIs
StatePublished - Oct 1 2018
Externally publishedYes

Fingerprint

Dysmenorrhea
Data Mining

Keywords

  • big data
  • data mining
  • dysmenorrhea
  • pelvic pain
  • women's health

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Big Data and Dysmenorrhea : What Questions Do Women and Men Ask about Menstrual Pain? / Chen, Chen; Groves, Doyle; Miller, Wendy; Carpenter, Janet.

In: Journal of Women's Health, Vol. 27, No. 10, 01.10.2018, p. 1233-1241.

Research output: Contribution to journalArticle

@article{7fa67d5996154c718de9a3ff488f2775,
title = "Big Data and Dysmenorrhea: What Questions Do Women and Men Ask about Menstrual Pain?",
abstract = "Background: Menstrual pain is highly prevalent among women of reproductive age. As the general public increasingly obtains health information online, Big Data from online platforms provide novel sources to understand the public's perspectives and information needs about menstrual pain. The study's purpose was to describe salient queries about dysmenorrhea using Big Data from a question and answer platform. Materials and Methods: We performed text-mining of 1.9 billion queries from ChaCha, a United States-based question and answer platform. Dysmenorrhea-related queries were identified by using keyword searching. Each relevant query was split into token words (i.e., meaningful words or phrases) and stop words (i.e., not meaningful functional words). Word Adjacency Graph (WAG) modeling was used to detect clusters of queries and visualize the range of dysmenorrhea-related topics. We constructed two WAG models respectively from queries by women of reproductive age and bymen. Salient themes were identified through inspecting clusters of WAG models. Results: We identified two subsets of queries: Subset 1 contained 507,327 queries from women aged 13-50 years. Subset 2 contained 113,888 queries from men aged 13 or above. WAG modeling revealed topic clusters for each subset. Between female and male subsets, topic clusters overlapped on dysmenorrhea symptoms and management. Among female queries, there were distinctive topics on approaching menstrual pain at school and menstrual pain-related conditions; while among male queries, there was a distinctive cluster of queries on menstrual pain from male's perspectives. Conclusions: Big Data mining of the ChaCha{\circledR} question and answer service revealed a series of information needs among women and men on menstrual pain. Findings may be useful in structuring the content and informing the delivery platform for educational interventions.",
keywords = "big data, data mining, dysmenorrhea, pelvic pain, women's health",
author = "Chen Chen and Doyle Groves and Wendy Miller and Janet Carpenter",
year = "2018",
month = "10",
day = "1",
doi = "10.1089/jwh.2017.6732",
language = "English (US)",
volume = "27",
pages = "1233--1241",
journal = "Journal of Women's Health",
issn = "1540-9996",
publisher = "Mary Ann Liebert Inc.",
number = "10",

}

TY - JOUR

T1 - Big Data and Dysmenorrhea

T2 - What Questions Do Women and Men Ask about Menstrual Pain?

AU - Chen, Chen

AU - Groves, Doyle

AU - Miller, Wendy

AU - Carpenter, Janet

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Background: Menstrual pain is highly prevalent among women of reproductive age. As the general public increasingly obtains health information online, Big Data from online platforms provide novel sources to understand the public's perspectives and information needs about menstrual pain. The study's purpose was to describe salient queries about dysmenorrhea using Big Data from a question and answer platform. Materials and Methods: We performed text-mining of 1.9 billion queries from ChaCha, a United States-based question and answer platform. Dysmenorrhea-related queries were identified by using keyword searching. Each relevant query was split into token words (i.e., meaningful words or phrases) and stop words (i.e., not meaningful functional words). Word Adjacency Graph (WAG) modeling was used to detect clusters of queries and visualize the range of dysmenorrhea-related topics. We constructed two WAG models respectively from queries by women of reproductive age and bymen. Salient themes were identified through inspecting clusters of WAG models. Results: We identified two subsets of queries: Subset 1 contained 507,327 queries from women aged 13-50 years. Subset 2 contained 113,888 queries from men aged 13 or above. WAG modeling revealed topic clusters for each subset. Between female and male subsets, topic clusters overlapped on dysmenorrhea symptoms and management. Among female queries, there were distinctive topics on approaching menstrual pain at school and menstrual pain-related conditions; while among male queries, there was a distinctive cluster of queries on menstrual pain from male's perspectives. Conclusions: Big Data mining of the ChaCha® question and answer service revealed a series of information needs among women and men on menstrual pain. Findings may be useful in structuring the content and informing the delivery platform for educational interventions.

AB - Background: Menstrual pain is highly prevalent among women of reproductive age. As the general public increasingly obtains health information online, Big Data from online platforms provide novel sources to understand the public's perspectives and information needs about menstrual pain. The study's purpose was to describe salient queries about dysmenorrhea using Big Data from a question and answer platform. Materials and Methods: We performed text-mining of 1.9 billion queries from ChaCha, a United States-based question and answer platform. Dysmenorrhea-related queries were identified by using keyword searching. Each relevant query was split into token words (i.e., meaningful words or phrases) and stop words (i.e., not meaningful functional words). Word Adjacency Graph (WAG) modeling was used to detect clusters of queries and visualize the range of dysmenorrhea-related topics. We constructed two WAG models respectively from queries by women of reproductive age and bymen. Salient themes were identified through inspecting clusters of WAG models. Results: We identified two subsets of queries: Subset 1 contained 507,327 queries from women aged 13-50 years. Subset 2 contained 113,888 queries from men aged 13 or above. WAG modeling revealed topic clusters for each subset. Between female and male subsets, topic clusters overlapped on dysmenorrhea symptoms and management. Among female queries, there were distinctive topics on approaching menstrual pain at school and menstrual pain-related conditions; while among male queries, there was a distinctive cluster of queries on menstrual pain from male's perspectives. Conclusions: Big Data mining of the ChaCha® question and answer service revealed a series of information needs among women and men on menstrual pain. Findings may be useful in structuring the content and informing the delivery platform for educational interventions.

KW - big data

KW - data mining

KW - dysmenorrhea

KW - pelvic pain

KW - women's health

UR - http://www.scopus.com/inward/record.url?scp=85055006979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055006979&partnerID=8YFLogxK

U2 - 10.1089/jwh.2017.6732

DO - 10.1089/jwh.2017.6732

M3 - Article

C2 - 29708827

AN - SCOPUS:85055006979

VL - 27

SP - 1233

EP - 1241

JO - Journal of Women's Health

JF - Journal of Women's Health

SN - 1540-9996

IS - 10

ER -