Table 2.

Top system performance within studies using machine learning or natural language processing (result metrics are reflected here as reported in the original publications).

Study	Classifier	MLa model	Features	Results reported
				Accuracy	F1 score	Area under curve
Pennacchiotti and Popescu, 2011 [68]	Binary	GBDTb	Images, text, topics, and sentiment	N/Ac	0.66	N/A
Pennacchiotti and Popescu, 2011 [67]	Binary	GBDT	Images, text, topics, sentiment, and network	N/A	0.70	N/A
Bergsma et al, 2013 [38]	Binary	SVMd	Names and name clusters	0.85	N/A	N/A
Ardehaly and Culotta, 2017 [35]	Binary	DLLPe	Text and images	N/A	0.95 (image); 0.92 (text)	N/A
Volkova and Backrach, 2018 [76]	Binary	LRf	Text, sentiment, and emotion	N/A	N/A	0.97
Wood-Doughtry et al, 2018 [79]	Binary	CNNg	Name	0.73	0.72	N/A
Saravanan, 2017 [72]	Ternary	CNN	Text	NRh	NR	NR
Ardehaly and Culotta, 2017 [33]	Ternary	DLLP	Text and images	N/A	0.84 (image); 0.83 (text)	N/A
Gunarathne et al, 2019 [94]	Ternary	CNN	Text	N/A	0.88	N/A
Wood-Doughtry et al, 2018 [79]	Ternary	CNN	Name	0.62	0.43	N/A
Culotta et al, 2016 [47]	Quaternary	Regression	Network and text	N/A	0.86	N/A
Chen et al, 2015 [46]	Quaternary	SVM	n-grams, topics, self-declarations, and image	0.79	0.79	0.72
Markson, 2017 [61]	Quaternary	CNN	Synonym expansion and topics	0.76	N/A	N/A
Wang et al, 2016 [189]	Quaternary	CNN	Images	0.84	N/A	N/A
Xu et al, 2016 [82]	Quaternary	SVM	Synonym expansion and topics	0.76	N/A	N/A
Ardehaly and Culotta, 2015 [34]	Quaternary	Multinomial logistic regression	Census, name, network, and tweet language	0.83	N/A	N/A
Ardehaly, 2014 [64]	Quaternary	LR	Census and image tweets	0.82	0.81	N/A
Barbera, 2016 [37]	Quaternary	LR with ENi	Tweets, emojis, and network	0.81	N/A	N/A
Wood-Doughty 2020 [81]	Quaternary	CNN	Name, profile metadata, and text	0.83	0.46	N/A
Preotiuc-Pietro and Ungar, 2018 [96]	Quaternary	LR with EN	Text, topics, sentiment, part-of-speech tagging, name, perceived race labels, and ensemble	N/A	N/A	0.88 (African American), 0.78 (Latino), 0.83 (Asian), and 0.83 (White)
Mueller et al, 2021 [91]	Quaternary	CNN	Text and accounts followed	N/A	0.25 (Asian), 0.63 (African American or Black), 0.28 (Hispanic), and 0.90 (White)	N/A
Bergsma et al, 2013 [38]	Multinomial (>4)	SVM	Name and name clusters	0.81	N/A	N/A
Nguyen et al, 2018 [66]	Multinomial (>4)	Neural network	Images	0.53	N/A	N/A

^aML: machine learning.

^bGBDT: gradient-boosted decision tree.

^cN/A: not applicable.

^dSVM: support vector machine.

^eDLLP: deep learning from label proportions.

^fLR: logistic regression.

^gCNN: convolutional neural network.

^hNR: not reported.

ⁱEN: elastic net.