Sentiment Analysis of Insomnia-Related Tweets via a Combination of Transformers Using Dempster-Shafer Theory: Pre- and Peri-COVID-19 Pandemic Retrospective Study.
Sentiment Analysis of Insomnia-Related Tweets via a Combination of Transformers Using Dempster-Shafer Theory: Pre- and Peri-COVID-19 Pandemic Retrospective Study.
复制标题
DOI：
10.2196/41517
复制
发表时间：
2022-12-27
影响因子：
7.4
通讯作者：
Razjouyan, Javad
中科院分区：
文献类型：
--
作者：
Maghsoudi, Arash;Nowakowski, Sara;Agrawal, Ritwick;Sharafkhaneh, Amir;Kunik, Mark E.;Naik, Aanand;Xu, Hua;Razjouyan, Javad
关键词：
COVID-19大流行给人群健康带来了额外的压力，这可能导致睡眠行为的改变。在这项研究中，我们假设使用自然语言处理来探索社交媒体将有助于评估COVID-19爆发后失眠症患者的心理健康状况。我们设计了一项回顾性研究，使用了Twitter上的公共社交媒体内容。我们根据时间对与失眠相关的推文进行了分类，使用了以下两个间隔：大流行前（2019年1月1日至2020年1月1日）和大流行期间（2020年1月1日至2021年1月1日）间隔。我们使用预先训练的变压器结合Dempster-Shafer理论（DST）进行了情绪分析，将情绪的极性分为积极、消极和中性。我们在300条带注释的tweet上验证了提议的管道。此外，我们使用逻辑回归进行了时间分析，以检验时间对Twitter用户失眠体验的影响。我们提取了305,321条包含失眠一词的推文（大流行前推文：n=139,561；大流行期间推文：n=165,760）。预训练变压器的最佳组合（通过DST组合）产生了84%的准确率。通过使用这个管道，我们发现发布负面推文的几率（比值比[OR] 1.39, 95% CI 1.37-1.41； P<.001）在大流行期间比在大流行前期间更高。午夜后发布负面推文的可能性比午夜前高21% （OR 1.21, 95% CI 1.19-1.23； P<.001）。在大流行前的时间间隔，午夜后发布负面推文的几率比午夜前高2% (OR 1.02, 95% CI 1.00-1.07； P= 0.008)，而在大流行前后的时间间隔，发布负面推文的几率比午夜前高43% （OR 1.43, 95% CI 1.40-1.46； P< 0.001）。提出的新的情感分析管道，结合了通过DST预训练的变压器，能够对失眠相关推文的情绪和情绪进行分类。推特用户在大流行期间分享的关于失眠的负面推文比大流行前期间更多。未来使用自然语言处理框架的研究可以评估关于其他类型的心理困扰、习惯改变、不活动导致的体重增加以及病毒感染对睡眠的影响的推文。
The COVID-19 pandemic has imposed additional stress on population health that may result in a change of sleeping behavior. In this study, we hypothesized that using natural language processing to explore social media would help with assessing the mental health conditions of people experiencing insomnia after the outbreak of COVID-19. We designed a retrospective study that used public social media content from Twitter. We categorized insomnia-related tweets based on time, using the following two intervals: the prepandemic (January 1, 2019, to January 1, 2020) and peripandemic (January 1, 2020, to January 1, 2021) intervals. We performed a sentiment analysis by using pretrained transformers in conjunction with Dempster-Shafer theory (DST) to classify the polarity of emotions as positive, negative, and neutral. We validated the proposed pipeline on 300 annotated tweets. Additionally, we performed a temporal analysis to examine the effect of time on Twitter users’ insomnia experiences, using logistic regression. We extracted 305,321 tweets containing the word insomnia (prepandemic tweets: n=139,561; peripandemic tweets: n=165,760). The best combination of pretrained transformers (combined via DST) yielded 84% accuracy. By using this pipeline, we found that the odds of posting negative tweets (odds ratio [OR] 1.39, 95% CI 1.37-1.41; P<.001) were higher in the peripandemic interval compared to those in the prepandemic interval. The likelihood of posting negative tweets after midnight was 21% higher than that before midnight (OR 1.21, 95% CI 1.19-1.23; P<.001). In the prepandemic interval, while the odds of posting negative tweets were 2% higher after midnight compared to those before midnight (OR 1.02, 95% CI 1.00-1.07; P=.008), they were 43% higher (OR 1.43, 95% CI 1.40-1.46; P<.001) in the peripandemic interval. The proposed novel sentiment analysis pipeline, which combines pretrained transformers via DST, is capable of classifying the emotions and sentiments of insomnia-related tweets. Twitter users shared more negative tweets about insomnia in the peripandemic interval than in the prepandemic interval. Future studies using a natural language processing framework could assess tweets about other types of psychological distress, habit changes, weight gain resulting from inactivity, and the effect of viral infection on sleep.
登录
查看更多内容
影响因子：
5
作者：
Colley, Rachel C.;Bushnik, Tracey;Langlois, Kellie
通讯作者：
Langlois, Kellie
影响因子：
4
作者：
Haman M
通讯作者：
Haman M
DOI：
10.2196/32449
发表时间：
2022-01
期刊：
JMIR infodemiology
影响因子：
--
作者：
通讯作者：
--
影响因子：
4.4
作者：
Mautong H;Gallardo-Rumbea JA;Alvarado-Villa GE;Fernández-Cadena JC;Andrade-Molina D;Orellana-Román CE;Cherrez-Ojeda I
通讯作者：
Cherrez-Ojeda I
影响因子：
4.8
作者：
Idrissi, Abdelkrim Janati;Lamkaddem, Abdelaziz;Souirti, Souhayr
通讯作者：
Souirti, Souhayr