"I Tried to Breastfeed but horizontal ellipsis ": Exploring Factors Influencing Breastfeeding Behaviours Based on Tweets Using Machine Learning and Thematic Analysis

被引:9
作者
Oyebode, Oladapo [1 ]
Lomotey, Richard [2 ]
Orji, Rita [1 ]
机构
[1] Dalhousie Univ, Fac Comp Sci, Halifax, NS B3H 1W5, Canada
[2] Penn State Univ Beaver, Dept Informat Sci & Technol IST, Monaca, PA 15061 USA
基金
加拿大自然科学与工程研究理事会;
关键词
Support vector machines; Training; Sentiment analysis; Social networking (online); Blogs; Psychology; Machine learning; Breastfeeding; health informatics; lexicon-based approach; machine learning; sentiment analysis; social media; thematic analysis; PERCEPTIONS; SUPPORT; MOTHERHOOD; WORKPLACE; ATTITUDES; PROMOTE; IMPACT; WOMEN;
D O I
10.1109/ACCESS.2021.3073079
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Social media is a growing platform for health-related discourse, opinion and experience sharing, including breastfeeding. For instance, nursing mothers share their personal experiences and opinions about breastfeeding on social networks, such as Facebook and Twitter. Unravelling the sentiments behind these experiences will promote adequate knowledge of many challenges, benefits, and factors influencing breastfeeding behaviours. To achieve this, we mine breastfeeding-related tweets and then perform sentiment analysis of the tweets using lexicon-based and machine learning (ML) techniques with the aim of detecting their sentiment polarity (i.e., positive or negative). Specifically, we implement and compare four lexicon-based sentiment classifiers, as well as five ML-based classifiers. Our results show that VADER-EXT (our extended version of VADER) performed best with an overall F1-score of 82.4%, compared to the other lexicon-based classifiers. On the other hand, Support Vector Machine (SVM) outperformed the other four ML-based classifiers with an overall F1-score of 73.7%. The overall best performing classifier is then used in determining the sentiment polarity of tweets. Next, we conduct thematic analysis of both positive and negative tweets to identify the factors influencing breastfeeding behaviours either positively or negatively. Our findings reveal various health-related factors (such as lactational issues, medical issues, and nutritional issues), social factors, psychological factors, and situational factors affecting breastfeeding behaviours negatively. Also, perceived benefits, maternal self-efficacy, social support, and education and training support emerged as the positive factors influencing breastfeeding behaviours. Finally, we reflect on our findings and recommend interventions that address the negative factors to promote positive breastfeeding behaviours.
引用
收藏
页码:61074 / 61089
页数:16
相关论文
共 61 条
[1]   Coparenting Breastfeeding Support and Exclusive Breastfeeding: A Randomized Controlled Trial [J].
Abbass-Dick, Jennifer ;
Stern, Susan B. ;
Nelson, LaRon E. ;
Watson, William ;
Dennis, Cindy-Lee .
PEDIATRICS, 2015, 135 (01) :102-110
[2]   Exosomes with immune modulatory features are present in human breast milk [J].
Admyre, Charlotte ;
Johansson, Sara M. ;
Qazi, Khaleda Rahman ;
Filen, Jan-Jonas ;
Lahesmaa, Riitta ;
Norman, Mikael ;
Neve, Etienne P. A. ;
Scheynius, Annika ;
Gabrielsson, Susanne .
JOURNAL OF IMMUNOLOGY, 2007, 179 (03) :1969-1978
[3]  
[Anonymous], 2018, Global Breastfeeding Scorecard
[4]  
[Anonymous], 2019, US Social Media Users, by Generation, 2019
[5]  
[Anonymous], 2011, Evaluating learning algorithms: A classification perspective, DOI DOI 10.1017/CBO9780511921803
[6]   The emotional resonances of breastfeeding in public: The role of strangers in breastfeeding practice [J].
Boyer, Kate .
EMOTION SPACE AND SOCIETY, 2018, 26 :33-40
[7]  
Braun V., 2006, Qualitative Research in Psychology, V3, P77, DOI [DOI 10.1191/1478088706QP063OA, https://doi.org/10.1191/1478088706qp063oa]
[8]   Breastfeeding and maternal health outcomes: a systematic review and meta-analysis [J].
Chowdhury, Ranadip ;
Sinha, Bireshwar ;
Sankar, Mari Jeeva ;
Taneja, Sunita ;
Bhandari, Nita ;
Rollins, Nigel ;
Bahl, Rajiv ;
Martines, Jose .
ACTA PAEDIATRICA, 2015, 104 :96-113
[9]  
Daniulaityte Raminta, 2016, JMIR Public Health Surveill, V2, pe162
[10]  
De Smedt T, 2012, J MACH LEARN RES, V13, P2063