%0 Conference Paper %1 conf/ehealth/GrasserKMZ18 %A Gräßer, Felix %A Kallumadi, Surya %A Malberg, Hagen %A Zaunseder, Sebastian %B DH %D 2018 %E Kostkova, Patty %E Grasso, Floriana %E Castillo, Carlos %E Mejova, Yelena %E Bosman, Arnold %E Edelstein, Michael %I ACM %K absa inter-rater-agreement sentiment-analysis %P 121-125 %T Aspect-Based Sentiment Analysis of Drug Reviews Applying Cross-Domain and Cross-Data Learning. %U https://dl.acm.org/doi/10.1145/3194658.3194677 %X Online review sites and opinion forums contain a wealth of information regarding user preferences and experiences over multiple product domains. This information can be leveraged to obtain valuable insights using data mining approaches such as sentiment analysis. In this work we examine online user reviews within the pharmaceutical field. Online user reviews in this domain contain information related to multiple aspects such as effectiveness of drugs and side effects, which make automatic analysis very interesting but also challenging. However, analyzing sentiments concerning the various aspects of drug reviews can provide valuable insights, help with decision making and improve monitoring public health by revealing collective experience. In this preliminary work we perform multiple tasks over drug reviews with data obtained by crawling online pharmaceutical review sites. We first perform sentiment analysis to predict the sentiments concerning overall satisfaction, side effects and effectiveness of user reviews on specific drugs. To meet the challenge of lacking annotated data we further investigate the transferability of trained classification models among domains, i.e. conditions, and data sources. In this work we show that transfer learning approaches can be used to exploit similarities across domains and is a promising approach for cross-domain sentiment analysis.

@inproceedings{conf/ehealth/GrasserKMZ18, abstract = {Online review sites and opinion forums contain a wealth of information regarding user preferences and experiences over multiple product domains. This information can be leveraged to obtain valuable insights using data mining approaches such as sentiment analysis. In this work we examine online user reviews within the pharmaceutical field. Online user reviews in this domain contain information related to multiple aspects such as effectiveness of drugs and side effects, which make automatic analysis very interesting but also challenging. However, analyzing sentiments concerning the various aspects of drug reviews can provide valuable insights, help with decision making and improve monitoring public health by revealing collective experience. In this preliminary work we perform multiple tasks over drug reviews with data obtained by crawling online pharmaceutical review sites. We first perform sentiment analysis to predict the sentiments concerning overall satisfaction, side effects and effectiveness of user reviews on specific drugs. To meet the challenge of lacking annotated data we further investigate the transferability of trained classification models among domains, i.e. conditions, and data sources. In this work we show that transfer learning approaches can be used to exploit similarities across domains and is a promising approach for cross-domain sentiment analysis.}, added-at = {2019-06-03T17:16:58.000+0200}, author = {Gräßer, Felix and Kallumadi, Surya and Malberg, Hagen and Zaunseder, Sebastian}, biburl = {https://www.bibsonomy.org/bibtex/2c5a9553f7fc2f55b8458616c219c3d5b/ghagerer}, booktitle = {DH}, crossref = {conf/ehealth/2018}, editor = {Kostkova, Patty and Grasso, Floriana and Castillo, Carlos and Mejova, Yelena and Bosman, Arnold and Edelstein, Michael}, ee = {https://doi.org/10.1145/3194658.3194677}, interhash = {2745967a9909e10c8f1cfba8ac1f84dc}, intrahash = {c5a9553f7fc2f55b8458616c219c3d5b}, keywords = {absa inter-rater-agreement sentiment-analysis}, pages = {121-125}, publisher = {ACM}, timestamp = {2020-05-23T17:16:31.000+0200}, title = {Aspect-Based Sentiment Analysis of Drug Reviews Applying Cross-Domain and Cross-Data Learning.}, url = {https://dl.acm.org/doi/10.1145/3194658.3194677}, year = 2018 }