Turning user generated health-related content into actionable knowledge through text analytics services

Text analytics in industry: Challenges, desiderata and trends

“…The limitations of TA techniques for certain domain-specific tasks and the added-value of expert knowledge were also highlighted in the study of [18]. Specifically, the proposed application fails in detecting drug names that are lexically realized as adjectives, for e.g.…”

“…The application for analyzing aviation safety reports presented in [16] relies on the TreeTagger toolkit [32] for PoStagging and lemmatization, while the Freeling toolkit [25] was used in [13] to process tweets. The application for processing health messages on social media in [18] made extensive use of the annotation pipeline from the GATE toolkit [44]. To classify texts, [16] and [14] respectively use the SVM implementation provided by the Liblinear [33] and Weka [28] libraries.…”

“…For e.g. [14] relied on the F-EXT webservices [26] for processing tweets, while [18] relied on webservices from MeaningCloud to process social media messages. The adoption of webservices in the TA community reflects a similar trend in the enterprise arena, where webservices are expected to play an increasingly important role.…”

“…The search-engine should be able to reliably pre-process all these different types of documents and index their contents. Similarly, the application for detecting ADR presented in [18] has to mine relevant information from different social media sources, such as Twitter and web forums. Thus, industrial TA applications should be sufficiently flexible so as to support and process texts in a wide variety of formats and from multiple sources.…”

“…Our review of the current state-of-the-art will be based on the scientific articles published in this special issue of the Computers in Industry journal 2 on text analytics in industry, namely [12][13][14][15][16][17][18].…”