The ever-growing volume of brand-related conversations on social media platforms has captivated the attention of academics and practitioners, as the analysis of those conversations promises to offer unparalleled insight into consumers’ emotions. This article takes a step back from the hype, and investigates the vulnerabilities related to the analysis of social media data concerning consumers’ sentiment. A review of the literature indicates that the form, focus, source and context of the communication may negatively impact on the analyst’s ability to identify sentiment polarity and emotional state. Likewise, the selection of analytical tool, the creation of codes, and the classification of the data, adversely affect the researcher’s ability to accurately assess the sentiment expressed in a social media conversation. Our study of Twitter conversations about coffee shows low levels of agreement between manual and automated analysis, which is of grave concern given the popularity of the latter in consumer research.
%0 Journal Article
%1 canhoto2015we
%A Canhoto, Ana Isabel
%A Padmanabhan, Yuvraj
%D 2015
%I Taylor & Francis
%J Journal of Marketing Management
%K human-vs-machine inter-rater-agreement sentiment-analysis social-media
%N 9-10
%P 1141--1157
%T ‘We (don’t) know how you feel’--a comparative study of automated vs. manual analysis of social media conversations
%U https://www.tandfonline.com/doi/pdf/10.1080/0267257X.2015.1047466?needAccess=true
%V 31
%X The ever-growing volume of brand-related conversations on social media platforms has captivated the attention of academics and practitioners, as the analysis of those conversations promises to offer unparalleled insight into consumers’ emotions. This article takes a step back from the hype, and investigates the vulnerabilities related to the analysis of social media data concerning consumers’ sentiment. A review of the literature indicates that the form, focus, source and context of the communication may negatively impact on the analyst’s ability to identify sentiment polarity and emotional state. Likewise, the selection of analytical tool, the creation of codes, and the classification of the data, adversely affect the researcher’s ability to accurately assess the sentiment expressed in a social media conversation. Our study of Twitter conversations about coffee shows low levels of agreement between manual and automated analysis, which is of grave concern given the popularity of the latter in consumer research.
@article{canhoto2015we,
abstract = {The ever-growing volume of brand-related conversations on social media platforms has captivated the attention of academics and practitioners, as the analysis of those conversations promises to offer unparalleled insight into consumers’ emotions. This article takes a step back from the hype, and investigates the vulnerabilities related to the analysis of social media data concerning consumers’ sentiment. A review of the literature indicates that the form, focus, source and context of the communication may negatively impact on the analyst’s ability to identify sentiment polarity and emotional state. Likewise, the selection of analytical tool, the creation of codes, and the classification of the data, adversely affect the researcher’s ability to accurately assess the sentiment expressed in a social media conversation. Our study of Twitter conversations about coffee shows low levels of agreement between manual and automated analysis, which is of grave concern given the popularity of the latter in consumer research.},
added-at = {2019-06-03T15:51:23.000+0200},
author = {Canhoto, Ana Isabel and Padmanabhan, Yuvraj},
biburl = {https://www.bibsonomy.org/bibtex/203bcd5dcfb1dafcf99e2f01b4b3fbd62/ghagerer},
interhash = {390eaecac8b29f7902feb1f815e64a9f},
intrahash = {03bcd5dcfb1dafcf99e2f01b4b3fbd62},
journal = {Journal of Marketing Management},
keywords = {human-vs-machine inter-rater-agreement sentiment-analysis social-media},
number = {9-10},
pages = {1141--1157},
publisher = {Taylor & Francis},
timestamp = {2019-06-03T16:00:16.000+0200},
title = {‘We (don’t) know how you feel’--a comparative study of automated vs. manual analysis of social media conversations},
url = {https://www.tandfonline.com/doi/pdf/10.1080/0267257X.2015.1047466?needAccess=true},
volume = 31,
year = 2015
}