BibTeX

@inproceedings{WCDMNARTTM19,
	author	 = {Max Lübbering and Julian Kunkel and Patricio Farrell},
	title	 = {{What Company Does My News Article Refer to? Tackling Multi Class Problems With Topic Modeling}},
	year	 = {2019},
	month	 = {09},
	booktitle	 = {{Proceedings of the Conference on "Lernen, Wissen, Daten, Analysen",
               Berlin, Germany, September 30 - October 2, 2019}},
	editor	 = {Robert Jäschke and Matthias Weidlich},
	publisher	 = {CEUR-WS.org},
	series	 = {CEUR Workshop Proceedings},
	number	 = {2454},
	pages	 = {353--364},
	conference	 = {LWDA 2019},
	location	 = {Berlin, Germany},
	abstract	 = {While it is technically trivial to search for the company name to predict the company a new article refers to, it often leads to wrong results. In this article, we compare the two approaches bag-of-words with k-nearest neighbors and Latent Dirichlet Allocation with k-nearest neighbor by assessing their applicability for predicting the S\&P 500 company which is mentioned in a business news article or press release. Both approaches are evaluated on a corpus of 13k documents containing 84\% news articles and 16\% press releases. While the bag-of-words approach yields accurate predictions, it is highly inefficient due to its gigantic feature space. The Latent Dirichlet Allocation approach, on the other hand, manages to achieve roughly the same prediction accuracy (0.58 instead of 0.62) but reduces the feature space by a factor of seven.},
	url	 = {https://pages.cms.hu-berlin.de/ipa/lwda2019/},
}