Word Clouds for Efficient Document Labeling

Seifert, Christin; Ulbrich, Eva

doi:10.1007/978-3-642-24477-3_24

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in our algorithm annotators label only a few topics based on their top 30 most probable words or phrases, without reading a document in the corpus. Hence, our algorithm requires even less labeling efforts as compared to Seifert et al [26].…”

Section: Discussionmentioning

confidence: 96%

“…In Seifert et al [26], annotators have to annotate key phrases in all documents in the corpus. However, in our algorithm annotators label only a few topics based on their top 30 most probable words or phrases, without reading a document in the corpus.…”

Section: Discussionmentioning

confidence: 99%

“…Seifert et al [26] propose an approach based on word clouds to generate training documents for text classification. They ask annotators to annotate condensed representation of documents, instead of the full text document for labeling single documents.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Topic labeled text classification

Hingmire

Chakraborti

2014

Proceedings of the 37th International ACM SIGIR Conference on Research &Amp; Development in Information Retrieval

View full text Add to dashboard Cite

Supervised text classifiers require extensive human expertise and labeling efforts. In this paper, we propose a weakly supervised text classification algorithm based on the labeling of Latent Dirichlet Allocation (LDA) topics. Our algorithm is based on the generative property of LDA. In our algorithm, we ask an annotator to assign one or more class labels to each topic, based on its most probable words. We classify a document based on its posterior topic proportions and the class labels of the topics. We also enhance our approach by incorporating domain knowledge in the form of labeled words. We evaluate our approach on four real world text classification datasets. The results show that our approach is more accurate in comparison to semi-supervised techniques from previous work. A central contribution of this work is an approach that delivers effectiveness comparable to the state-of-the-art supervised techniques in hard-toclassify domains, with very low overheads in terms of manual knowledge engineering.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 99%