Media Releases and Opportunities

» Go to news main

Media opportunity: Social media and machine learning offers insight into experiences of breastfeeding mothers, can inform public policy: Canadian, U.S. researchers

Posted by Communications and Marketing on May 11, 2021 in News

Social media has become a popular platform for new mothers to openly share their personal experiences of parenthood, be it the highs of bonding with their new baby or the frustration of getting them to latch properly while breastfeeding.

Researchers at Dalhousie University and Penn State have tapped into that data stream to unravel the sentiments nursing mothers’ express in tweets and better understand the factors influencing breastfeeding behaviours.

Dr. Rita Orji, an associate professor of Computer Science and a Canada Research Chair in Persuasive Technology at Dal who specializes in human-computer interaction, worked with a colleague at Penn State Beaver to collect more than 19,000 tweets related to breastfeeding. Using lexicon-based tools and new machine learning classifiers that they developed, the pair was able to mine the data and classify them as positive or negative.

They identified 29 negative and 21 positive themes and while most negative factors affecting breastfeeding have been reported previously, the researchers uncovered some new challenges, including the deliberate decision to not breastfeed and fear of biting.

They hope the findings in their study can inform policies and interventions to improve resources for nursing mothers, such as workplace accommodations and technological aids such as apps.

Dr. Orji is available to discuss how the tweets capture the real challenges and joys experienced by breastfeeding mothers, and how that information can help create supports that allow women to succeed.

                                                                                - 30 -

Media contact:
Alison Auld
Senior Research Reporter
Dalhousie University
Cell: 1-902-220-0491


All comments require a name and email address. You may also choose to log-in using your preferred social network or register with Disqus, the software we use for our commenting system. Join the conversation, but keep it clean, stay on the topic and be brief. Read comments policy.

comments powered by Disqus