Harnessing the Power of Social Media Data to Generate Oncology Insights

Cancer patients are increasingly going online to share their experiences as well as hopes and fears for the future. Much of the content generated by patients, caregivers, and HCPs can be used to help us understand the cancer journey. As part of our Oncology Insights series, we aim to uncover the statistics, trends, and pearls unique to each type of cancer.

We use the JUICE AMP tool to uncover these insights. JUICE AMP is a platform that uses natural language processing to analyze conversations and other online content across different disease states. The tool helps us find critical insights and provides an opportunity to connect with patients.

We start our series with a high level overview of social media statistics on breast cancer. Breast cancer is the second most commonly diagnosed cancer among American women.

Within a 6-month time frame (July 2015December 2015), there were 221,839 posts about breast cancer from 165,035 unique posters across platforms that include Facebook, Google, Twitter, Tumblr, and YouTube. Posters included patients, caregivers, HCPs, journalists, and other contributors.

Most of the online conversations focused on symptoms and diagnosis. Specific experiences with procedures and treatments were secondary topics.


In terms of diagnosis, triple negative breast cancer emerged as the most widely discussed (5,327 posts), even though TNBC accounts for only 15% to 20% of breast cancers in the United States. On the contrary, invasive ductal carcinoma is the most common type of breast cancer (80% of all breast cancers), but there were only 332 posts that mentioned this type. There was a lot of discussion about BRCA+ breast cancer. Five percent to 10% of breast cancers are due to a gene mutation such as BRCA1/BRCA2. Ductal carcinoma in situ, the most common type of non-invasive breast cancer, came in third in terms of mentions. Much fewer posts mentioned inflammatory breast cancer, which is a rare and very aggressive type of breast cancer.


Hundreds of posts detailed the specific procedures related to breast cancer, with mammograms being the most widely discussed in over 28,000 posts. The most common surgical procedure mentioned was a mastectomy (12,798 posts).


Treatment involves a mix of options depending on the type and stage of breast cancer. Chemotherapy and radiation were the most talked about. In terms of hormone therapy, Tamoxifen (brand name: Nolvadex) was mentioned the most. The most-discussed targeted therapy was Herceptin.


Behind these social media statistics are real people dealing with breast cancer. Many detail their journey through the different stages. In a future post, we will dig deeper into the emotional journey of breast cancer patients.

By Phung Nguyen, Senior Research Manager
JUICE Pharma Worldwide