TY - JOUR
T1 - Understanding users' vaping experiences from social media
T2 - Initial study using sentiment opinion summarization techniques
AU - Li, Qiudan
AU - Wang, Can
AU - Liu, Ruoran
AU - Wang, Lei
AU - Zeng, Daniel Dajun
AU - Leischow, Scott
N1 - Funding Information:
This work was supported by the National Key R&D Program of China under Grant No. 2016QY02D0305,the US National Institutes of Health under Grant No. 5R01DA037378-05, National Natural Science Foundation of China under Grant Nos. 61671450, 71621002, 71272236, and The Key Research Program of the Chinese Academy of Sciences under Grant No. ZDRW-XH-2017-3.
Publisher Copyright:
© Qiudan Li, Can Wang, Ruoran Liu, Lei Wang, Daniel Dajun Zeng, Scott James Leischow. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 15.08.2018. This is an open-access article distributed under the terms of the Creative Commons Attribution License.
PY - 2018/8
Y1 - 2018/8
N2 - Background: E-liquid is one of the main components in electronic nicotine delivery systems (ENDS). ENDS review comments could serve as an early warning on use patterns and even function to serve as an indicator of problems or adverse events pertaining to the use of specific e-liquids-much like types of responses tracked by the Food and Drug Administration (FDA) regarding medications. Objective: This study aimed to understand users' “vaping” experience using sentiment opinion summarization techniques, which can help characterize how consumers think about specific e-liquids and their characteristics (eg, flavor, throat hit, and vapor production). Methods: We collected e-liquid reviews on JuiceDB from June 27, 2013 to December 31, 2017 using its public application programming interface. The dataset contains 27,070 reviews for 8058 e-liquid products. Each review is accompanied by an overall rating and a set of 4 aspect ratings of an e-liquid, each on a scale of 1-5: flavor accuracy, throat hit, value, and cloud production. An iterative dichotomiser 3 (ID3)-based influential aspect analysis model was adopted to learn the key elements that impact e-liquid use. Then, fine-grained sentiment analysis was employed to mine opinions on various aspects of vaping experience related to e-liquids. Results: We found that flavor accuracy and value were the two most important aspects that affected users' sentiments toward e-liquids. Of reviews in JuiceDB, 67.83% (18,362/27,070) were positive, while 12.67% (3430/27,070) were negative. This indicates that users generally hold positive attitudes toward e-liquids. Among the 9 flavors, fruity and sweet were the two most popular. Great and sweet tastes, reasonable value, and strong throat hit made users satisfied with fruity and sweet flavors, whereas “strange” tastes made users dislike those flavors. Meanwhile, users complained about some e-liquids' steep or expensive prices, bad quality, and harsh throat hit. There were 2342 fruity e-liquids and 2049 sweet e-liquids. There were 55.81% (1307/2342) and 59.83% (1226/2049) positive sentiments and 13.62% (319/2342) and 12.88% (264/2049) negative sentiments toward fruity e-liquids and sweet e-liquids, respectively. Great flavors and good vapors contributed to positive reviews of fruity and sweet products. However, bad tastes such as “sour” or “bitter” resulted in negative reviews. These findings can help businesses and policy makers to further improve product quality and formulate effective policy. Conclusions: This study provides an effective mechanism for analyzing users' ENDS vaping experience based on sentiment opinion summarization techniques. Sentiment opinions on aspect and products can be found using our method, which is of great importance to monitor e-liquid products and improve work efficiency.
AB - Background: E-liquid is one of the main components in electronic nicotine delivery systems (ENDS). ENDS review comments could serve as an early warning on use patterns and even function to serve as an indicator of problems or adverse events pertaining to the use of specific e-liquids-much like types of responses tracked by the Food and Drug Administration (FDA) regarding medications. Objective: This study aimed to understand users' “vaping” experience using sentiment opinion summarization techniques, which can help characterize how consumers think about specific e-liquids and their characteristics (eg, flavor, throat hit, and vapor production). Methods: We collected e-liquid reviews on JuiceDB from June 27, 2013 to December 31, 2017 using its public application programming interface. The dataset contains 27,070 reviews for 8058 e-liquid products. Each review is accompanied by an overall rating and a set of 4 aspect ratings of an e-liquid, each on a scale of 1-5: flavor accuracy, throat hit, value, and cloud production. An iterative dichotomiser 3 (ID3)-based influential aspect analysis model was adopted to learn the key elements that impact e-liquid use. Then, fine-grained sentiment analysis was employed to mine opinions on various aspects of vaping experience related to e-liquids. Results: We found that flavor accuracy and value were the two most important aspects that affected users' sentiments toward e-liquids. Of reviews in JuiceDB, 67.83% (18,362/27,070) were positive, while 12.67% (3430/27,070) were negative. This indicates that users generally hold positive attitudes toward e-liquids. Among the 9 flavors, fruity and sweet were the two most popular. Great and sweet tastes, reasonable value, and strong throat hit made users satisfied with fruity and sweet flavors, whereas “strange” tastes made users dislike those flavors. Meanwhile, users complained about some e-liquids' steep or expensive prices, bad quality, and harsh throat hit. There were 2342 fruity e-liquids and 2049 sweet e-liquids. There were 55.81% (1307/2342) and 59.83% (1226/2049) positive sentiments and 13.62% (319/2342) and 12.88% (264/2049) negative sentiments toward fruity e-liquids and sweet e-liquids, respectively. Great flavors and good vapors contributed to positive reviews of fruity and sweet products. However, bad tastes such as “sour” or “bitter” resulted in negative reviews. These findings can help businesses and policy makers to further improve product quality and formulate effective policy. Conclusions: This study provides an effective mechanism for analyzing users' ENDS vaping experience based on sentiment opinion summarization techniques. Sentiment opinions on aspect and products can be found using our method, which is of great importance to monitor e-liquid products and improve work efficiency.
KW - E-cigarette
KW - E-liquid
KW - Electronic nicotine delivery systems
KW - Infodemiology
KW - JuiceDB
KW - Sentiment opinion summarization
KW - Social media
KW - Vaping
UR - http://www.scopus.com/inward/record.url?scp=85052906087&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052906087&partnerID=8YFLogxK
U2 - 10.2196/jmir.9373
DO - 10.2196/jmir.9373
M3 - Article
C2 - 30111530
AN - SCOPUS:85052906087
SN - 1439-4456
VL - 20
JO - Journal of medical Internet research
JF - Journal of medical Internet research
IS - 8
M1 - e252
ER -