Wyniki wyszukiwania - Biblioteka Nauki

1

Leveraging Unseen Features along with their PLM-based Representation to Handle Negative Covariate Shift Problem in Text Classification

100%

Wasi N. A. , Abulaish M.

Foundations of Computing and Decision Sciences

|

2024

|

tom Vol. 49, No. 4

409--430

EN

This paper presents a novel approach to address the problem of negative covariate shift by using unseen features. Covariate shift occurs when there is a drift between the data observed during the training and testing phase of a machine learning model. Covariate shift typically transpires in the negative class as a consequence of the swift evolution of topics discussed therein, which is driven by the characteristics of online social media. Because there is a shift in data, it signals that the data is changing, and it includes features that the trained model did not see during the training phase. We refer to such features as unseen features. To the best of our knowledge, we are the first to use unseen features to address negative covariate shift problem. The proposed approach is compared to three baselines and one state-of-the art method. The experimental results obtained from a multi-domain sentiment dataset show that the proposed approach outperforms the baselines and state-of-the-art approaches by a significant margin in terms of various performance evaluation metrics.

2

Bag of words and embedding text representation methods for medical article classification

86%

Cichosz P.

International Journal of Applied Mathematics and Computer Science

|

2023

|

tom Vol. 33, no. 4

603--621

EN

Text classification has become a standard component of automated systematic literature review (SLR) solutions, where articles are classified as relevant or irrelevant to a particular literature study topic. Conventional machine learning algorithms for tabular data which can learn quickly from not necessarily large and usually imbalanced data with low computational demands are well suited to this application, but they require that the text data be transformed to a vector representation. This work investigates the utility of different types of text representations for this purpose. Experiments are presented using the bag of words representation and selected representations based on word or text embeddings: word2vec, doc2vec, GloVe, fastText, Flair, and BioBERT. Four classification algorithms are used with these representations: a naive Bayes classifier, logistic regression, support vector machines, and random forest. They are applied to datasets consisting of scientific article abstracts from systematic literature review studies in the medical domain and compared with the pre-trained BioBERT model fine-tuned for classification. The obtained results confirm that the choice of text representation is essential for successful text classification. It turns out that, while the standard bag of words representation is hard to beat, fastText word embeddings make it possible to achieve roughly the same level of classification quality with the added benefit of much lower dimensionality and capability of handling out-of-vocabulary words. More refined embeddings methods based on deep neural networks, while much more demanding computationally, do not appear to offer substantial advantages for the classification task. The fine-tuned BioBERT classification model performs on par with conventional algorithms when they are coupled with their best text representation methods.

3

An Empirical Study on Application of Word Embedding Techniques for Prediction of Software Defect Severity Level

72%

Kumar L. , Kumar M. , Bhanu Murthy L. , Misra S. , Kocher V. , Padmanabhuni S.

Annals of Computer Science and Information Systems

|

2021

|

tom Vol. 25

477--484

EN

This work aims to develop defect severity level prediction models that have the ability to assign severity level of defects based on bugs report. In this work, seven different word embedding techniques are applied to defect description to represent the word, not just as a number but as a vector in n-dimensional space. Further, three feature selection techniques have been applied to find the right set of relevant vectors. The effectiveness of these word embedding techniques and different sets of vectors are evaluated using different classification techniques with SMOTE to overcome the class imbalance problem.

4

A case study in text mining of discussion forum posts: Classification with bag of words and global vectors

72%

Cichosz P.

International Journal of Applied Mathematics and Computer Science

|

2018

|

tom Vol. 28, no. 4

787--801

EN

Despite the rapid growth of other types of social media, Internet discussion forums remain a highly popular communication channel and a useful source of text data for analyzing user interests and sentiments. Being suited to richer, deeper, and longer discussions than microblogging services, they particularly well reflect topics of long-term, persisting involvement and areas of specialized knowledge or experience. Discovering and characterizing such topics and areas by text mining algorithms is therefore an interesting and useful research direction. This work presents a case study in which selected classification algorithms are applied to posts from a Polish discussion forum devoted to psychoactive substances received from home-grown plants, such as hashish or marijuana. The utility of two different vector text representations is examined: the simple bag of words representation and the more refined embedded global vectors one. While the former is found to work well for the multinomial naive Bayes algorithm, the latter turns out more useful for other classification algorithms: logistic regression, SVMs, and random forests. The obtained results suggest that post-classification can be applied for measuring publication intensity of particular topics and, in the case of forums related to psychoactive substances, for monitoring the risk of drug-related crime.

5

Comparative Analysis of Word Embedding and Machine Learning Techniques for Classification of Software Developer Communications on Gitter

58%

Akshar T. , Kumar L. , Yogita , Murthy L. B.

Annals of Computer Science and Information Systems

|

2023

|

tom Vol. 35

335--346

EN

In recent times, software developers widely use instant messaging and collaboration platforms, as these platforms aid them in exploring new technologies, raising different development-related issues, and seeking solutions from their peers virtually. Gitter is one such platform that has a heavy userbase. It generates a tremendous volume of data, analysis of which is helpful to gain insights about trends in open-source software development and the developers' inclination toward various technologies. The classification techniques can be deployed for this purpose. The selection of an apt word embedding for a given dataset of text messages plays a vital role in determining the performance of classification techniques. In the present work, the comparative analysis of nine-word embeddings in combination with seventeen classification techniques with onevsone and onevsrest has been performed on the GitterCom dataset for categorizing text messages into one of the pre-determined classes based on their purpose. Further, two feature selection methods have been applied. The SMOTE technique has been used for handling data imbalance. It resulted in a total of 612 classification pipelines for analysis. The experimental results show that word2vect, GLOVE with 300 vector size, and GLOVE with 100 vector size are three top-performing word embeddings having performance values taken across different classification techniques. The models trained using ANOVA features performed similarly to those models trained using all features. Finally, using the SMOTE technique helps models to get a better prediction ability.