Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898339904> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2898339904 endingPage "38" @default.
- W2898339904 startingPage "20" @default.
- W2898339904 abstract "Abstract Online social media drive the growth of unstructured text data. Many marketing applications require structuring this data at scales non-accessible to human coding, e.g., to detect communication shifts in sentiment or other researcher-defined content categories. Several methods have been proposed to automatically classify unstructured text. This paper compares the performance of ten such approaches (five lexicon-based, five machine learning algorithms) across 41 social media datasets covering major social media platforms, various sample sizes, and languages. So far, marketing research relies predominantly on support vector machines (SVM) and Linguistic Inquiry and Word Count (LIWC). Across all tasks we study, either random forest (RF) or naive Bayes (NB) performs best in terms of correctly uncovering human intuition. In particular, RF exhibits consistently high performance for three-class sentiment, NB for small samples sizes. SVM never outperform the remaining methods. All lexicon-based approaches, LIWC in particular, perform poorly compared with machine learning. In some applications, accuracies only slightly exceed chance. Since additional considerations of text classification choice are also in favor of NB and RF, our results suggest that marketing research can benefit from considering these alternatives." @default.
- W2898339904 created "2018-11-02" @default.
- W2898339904 creator A5033505913 @default.
- W2898339904 creator A5047780355 @default.
- W2898339904 creator A5062843383 @default.
- W2898339904 creator A5090071130 @default.
- W2898339904 date "2019-03-01" @default.
- W2898339904 modified "2023-10-18" @default.
- W2898339904 title "Comparing automated text classification methods" @default.
- W2898339904 cites W1980399432 @default.
- W2898339904 cites W2012070465 @default.
- W2898339904 cites W2039076910 @default.
- W2898339904 cites W2048658075 @default.
- W2898339904 cites W2100483895 @default.
- W2898339904 cites W2114535528 @default.
- W2898339904 cites W2117332653 @default.
- W2898339904 cites W2118020653 @default.
- W2898339904 cites W2140785063 @default.
- W2898339904 cites W2142827986 @default.
- W2898339904 cites W2143455647 @default.
- W2898339904 cites W2145855348 @default.
- W2898339904 cites W2157289081 @default.
- W2898339904 cites W2161336914 @default.
- W2898339904 cites W2182461851 @default.
- W2898339904 cites W2283968330 @default.
- W2898339904 cites W2291815641 @default.
- W2898339904 cites W2487586139 @default.
- W2898339904 cites W2508425776 @default.
- W2898339904 cites W2557711433 @default.
- W2898339904 cites W2761970766 @default.
- W2898339904 cites W2911964244 @default.
- W2898339904 cites W2919115771 @default.
- W2898339904 cites W3121315632 @default.
- W2898339904 cites W3122125470 @default.
- W2898339904 cites W3123399111 @default.
- W2898339904 cites W3123432896 @default.
- W2898339904 cites W3124914435 @default.
- W2898339904 cites W3125545209 @default.
- W2898339904 cites W4212883601 @default.
- W2898339904 cites W4236726206 @default.
- W2898339904 cites W4239510810 @default.
- W2898339904 doi "https://doi.org/10.1016/j.ijresmar.2018.09.009" @default.
- W2898339904 hasPublicationYear "2019" @default.
- W2898339904 type Work @default.
- W2898339904 sameAs 2898339904 @default.
- W2898339904 citedByCount "210" @default.
- W2898339904 countsByYear W28983399042019 @default.
- W2898339904 countsByYear W28983399042020 @default.
- W2898339904 countsByYear W28983399042021 @default.
- W2898339904 countsByYear W28983399042022 @default.
- W2898339904 countsByYear W28983399042023 @default.
- W2898339904 crossrefType "journal-article" @default.
- W2898339904 hasAuthorship W2898339904A5033505913 @default.
- W2898339904 hasAuthorship W2898339904A5047780355 @default.
- W2898339904 hasAuthorship W2898339904A5062843383 @default.
- W2898339904 hasAuthorship W2898339904A5090071130 @default.
- W2898339904 hasBestOaLocation W28983399041 @default.
- W2898339904 hasConcept C154945302 @default.
- W2898339904 hasConcept C204321447 @default.
- W2898339904 hasConcept C23123220 @default.
- W2898339904 hasConcept C41008148 @default.
- W2898339904 hasConceptScore W2898339904C154945302 @default.
- W2898339904 hasConceptScore W2898339904C204321447 @default.
- W2898339904 hasConceptScore W2898339904C23123220 @default.
- W2898339904 hasConceptScore W2898339904C41008148 @default.
- W2898339904 hasFunder F4320320879 @default.
- W2898339904 hasIssue "1" @default.
- W2898339904 hasLocation W28983399041 @default.
- W2898339904 hasLocation W28983399042 @default.
- W2898339904 hasOpenAccess W2898339904 @default.
- W2898339904 hasPrimaryLocation W28983399041 @default.
- W2898339904 hasRelatedWork W2101955803 @default.
- W2898339904 hasRelatedWork W2119214692 @default.
- W2898339904 hasRelatedWork W2144190808 @default.
- W2898339904 hasRelatedWork W2151447942 @default.
- W2898339904 hasRelatedWork W2357241418 @default.
- W2898339904 hasRelatedWork W2366644548 @default.
- W2898339904 hasRelatedWork W2376314740 @default.
- W2898339904 hasRelatedWork W2384888906 @default.
- W2898339904 hasRelatedWork W2469626427 @default.
- W2898339904 hasRelatedWork W2611614995 @default.
- W2898339904 hasVolume "36" @default.
- W2898339904 isParatext "false" @default.
- W2898339904 isRetracted "false" @default.
- W2898339904 magId "2898339904" @default.
- W2898339904 workType "article" @default.