A novel multiple kernel fuzzy topic modeling technique for biomedical data

Abstract

Background Text mining in the biomedical field has received much attention and regarded as the important research area since a lot of biomedical data is in text format. Topic modeling is one of the popular methods among text mining techniques used to discover hidden semantic structures, so called topics. However, discovering topics from biomedical data is a challenging task due to the sparsity, redundancy, and unstructured format. Methods In this paper, we proposed a novel multiple kernel fuzzy topic modeling (MKFTM) technique using fusion probabilistic inverse document frequency and multiple kernel fuzzy c-means clustering algorithm for biomedical text mining. In detail, the proposed fusion probabilistic inverse document frequency method is used to estimate the weights of global terms while MKFTM generates frequencies of local and global terms with bag-of-words. In addition, the principal component analysis is applied to eliminate higher-order negative effects for term weights. Results Extensive experiments are conducted on six biomedical datasets. MKFTM achieved the highest classification accuracy 99.04%, 99.62%, 99.69%, 99.61% in the Muchmore Springer dataset and 94.10%, 89.45%, 92.91%, 90.35% in the Ohsumed dataset. The CH index value of MKFTM is higher, which shows that its clustering performance is better than state-of-the-art topic models. Conclusion We have confirmed from results that proposed MKFTM approach is very efficient to handles to sparsity and redundancy problem in biomedical text documents. MKFTM discovers semantically relevant topics with high accuracy for biomedical documents. Its gives better results for classification and clustering in biomedical documents. MKFTM is a new approach to topic modeling, which has the flexibility to work with a variety of clustering methods.

LIBAC: An Annotated Corpus for Automated “Reading” of the Lithium-Ion Battery Research Literature

“…Nevertheless, the cut-off of the F 1 -score (∼80%) was chosen due to the fact that NLP tasks do not receive much attention in the LIB literature, and SotA scores are lacking. In contrast, the biomedical community has made significant efforts to evaluate TM and IE systems, and it has for long been discussing NLP SotA, with their highest test scores already being close to 99% . Hence, further discussions about the acceptable accuracy rates that should be considered by the LIB community and how to improve it in the future will be therefore critically needed in the future.…”

Review of Survey Research in Fuzzy Approach for Text Mining

“…Rashid et al proposed a topic modeling technique for text mining by mixing inverse document frequency and fuzzy kmeans clustering algorithm in machine learning, which helped discover precise topics from biomedical text documents [127], Lossio-Ventura et al trained and compared topic modeling and clustering algorithm models for health-related tweets on social software, the results show that relevant researchers can choose an appropriate model according to the characteristics of the data [128], Karami et al used fuzzy latent semantic analysis (FLSA) for topic modeling applications in health and medical corpus redundancy problems and provided a new method for estimating the number of topics, the results show that FLSA produces performance and features superior to past research [129]. Rashid et al proposed a novel Multiple kernel fuzzy topic modeling (MKFTM) technology, which uses fusion probabilistic inverse document frequency and multiple kernel fuzzy c-means clustering algorithm methods for biomedical text mining, the fusion probabilistic inverse document frequency method is used to calculate the weight of the entire medical document, and then use the BOW vector model to convert the local vector of the paragraph and the entire document vector through MKFTM and perform document clustering to model [130], in addition, in order to reduce The impact of technical terms, the study also used principal component analysis for dimensionality reduction.…”

Latent Drug Recognition Using Fuzzy Matching in Sequential Analysis of Full-Text Health Related Publications: Case of a Health Dissemination tool in a developing country

“…In topic modelling approach by Rashid, et.al [34] utilized fuzzy k-means latent semantic analysis (FKLSA) on medical and health text corpora. Multiple kernel fuzzy topic modeling technique by J. Rashid, et.al [35] was proposed for biomedical text mining. Fuzzy LSA-W and FLSA-V [36] was applied to topic embeddings in text classi cation.…”