Topic Detection and Tracking Techniques on Twitter: A Systematic Review

Table 1

Twitter topic/event detection/tracking related studies.

Reference	Detection method	Detection type		Detection task		Data collection; Dataset	Detection task
		Event	Topic	RED	NED
[12]	Naïve Bayes classifier		✓		✓	Twitter API, handpicked users	Hot news detection
[13]	BScore based BOW clustering	✓			✓	Twitter API (offline)	Disaster and story detection
[14]	BOW distance similarity	✓			✓	Twitter API	FSD (first story detection)
[15]	BNgram and TF-IDF		✓	✓		Offline datasets	Topic detection
[16]	Cross checking via Wikipedia	✓			✓	Twitter API, Wikipedia	Hot news detection
[17]	Formal concept analysis		✓		✓	RepLab 2013 dataset	Topic detection
[18]	FPM (frequent pattern mining)	✓			✓	Twitter API	Event detection
[19]	FPM		✓	✓		Super Tuesday/FA Cup/US elections	Topic detection
[20]	FPM (hierarchical clustering)		✓		✓	Topic dataset from CLEar system	Topic detection
[21]	FPM (TF-IDF & n-gram improved)	✓			✓	Twitter API	Event detection
[22]	GPU improved TF-IDF approximation		✓	✓		Offline dataset	Topic detection
[23]	BOW similarity	✓			✓	Offline dataset	Topic detection
[24]	Word embedding					SemEval dataset	Twitter sentiment classification
[25]	Spatiotemporal detection	✓		✓		Offline dataset	Targeted-domain event detection
[26]	Clustering of temporal & spatial features	✓		✓		Twitter API	Event detection
[27]	Geographical regularity estimation	✓			✓	Twitter API	Geosocial event detection
[28]	BOW clustering	✓			✓	Twitter API	Event detection & analysis
[29]	Probabilistic modeling	✓			✓	Twitter API	Early disaster detection
[30]	FPM	✓		✓		Offline dataset	Event detection
[31]	Heartbeat graph	✓		✓		Super Tuesday/FA Cup/US elections	Topic/event detection
[32]	Enhanced heartbeat graph	✓		✓		Super Tuesday/FA Cup/US elections	Topic/event detection
[33]	Sentence BERT/streaming graph mining		✓	✓	✓	Super Tuesday/FA Cup/US elections	Topic/event detection
[34]	Universal sentence encoder		✓	✓	✓	COVID-19 dataset	COVID-19 topics
[35]	TF-IDF, CCA, and BTM		✓	✓		Twitter API	Trend ranking
[36]	LDA, USE, and SBERT	✓		✓		COVID-19 dataset	COVID-19 topics
[37]	Autoencoder and fuzzy c-means		✓	✓		Berita	Trend ranking