A Comparative Study on using Principle Component Analysis with different Text Classifiers

Taloba, Ahmed I.; Eisa, D. A.; Ismail, Safaa S. I.

doi:10.5120/ijca2018916800

Cited by 11 publications

(15 citation statements)

References 18 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, calculating the TF-IDF weight of a term in a particular document requires calculating term frequency [TF(t, d)], which is the number of times that the word t occurred in document d; document frequency [DF(t)], which is the number of documents in which term t occurs at least once; and inverse document frequency (IDF), which can be calculated from DF using the following formula. The IDF of a word is considered high if it occurred in a few documents and low if it occurred in many documents (Ahmed Taloba et al, 2018). The TF-IDF model is defined in Equations ( 2) and ( 3):…”

Section: Data Preprocessingmentioning

confidence: 99%

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Albalawi

Yeap

Benyoucef

2020

Front. Artif. Intell.

228

130

View full text Add to dashboard Cite

With the growth of online social network platforms and applications, large amounts of textual user-generated content are created daily in the form of comments, reviews, and short-text messages. As a result, users often find it challenging to discover useful information or more on the topic being discussed from such content. Machine learning and natural language processing algorithms are used to analyze the massive amount of textual social media data available online, including topic modeling techniques that have gained popularity in recent years. This paper investigates the topic modeling subject and its common application areas, methods, and tools. Also, we examine and compare five frequently used topic modeling methods, as applied to short textual social data, to show their benefits practically in detecting important topics. These methods are latent semantic analysis, latent Dirichlet allocation, non-negative matrix factorization, random projection, and principal component analysis. Two textual datasets were selected to evaluate the performance of included topic modeling methods based on the topic quality and some standard statistical evaluation metrics, like recall, precision, F -score, and topic coherence. As a result, latent Dirichlet allocation and non-negative matrix factorization methods delivered more meaningful extracted topics and obtained good results. The paper sheds light on some common topic modeling methods in a short-text context and provides direction for researchers who seek to apply these methods.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Albalawi

Yeap

Benyoucef

2020

Front. Artif. Intell.

228

130

View full text Add to dashboard Cite

show abstract

“…On the other hand, in feature extraction methods, a new vector space with special characteristics is created by transforming the original vector space. The features are reduced in new vector space [32].…”

Section: B Dimensionality Reduction Methodsmentioning

confidence: 99%

“…One of the most popular statistical techniques for feature selection is PCA [32]. The discriminative power of the classifiers can be enhanced by utilizing PCA.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)

et al. 2020

View full text Add to dashboard Cite

Society and individuals are negatively influenced both politically and socially by the widespread increase of fake news either way generated by humans or machines. In the era of social networks, the quick rotation of news makes it challenging to evaluate its reliability promptly. Therefore, automated fake news detection tools have become a crucial requirement. To address the aforementioned issue, a hybrid Neural Network architecture, that combines the capabilities of CNN and LSTM, is used with two different dimensionality reduction approaches, Principle Component Analysis (PCA) and Chi-Square. This work proposed to employ the dimensionality reduction techniques to reduce the dimensionality of the feature vectors before passing them to the classifier. To develop the reasoning, this work acquired a dataset from the Fake News Challenges (FNC) website which has four types of stances: agree, disagree, discuss, and unrelated. The nonlinear features are fed to PCA and chi-square which provides more contextual features for fake news detection. The motivation of this research is to determine the relative stance of a news article towards its headline. The proposed model improves results by ∼ 4% and ∼ 20% in terms of Accuracy and F 1 − score. The experimental results show that PCA outperforms than Chi-square and state-of-the-art methods with 97.8% accuracy.

show abstract

“…We decided to use the kNN classification approach as data was recorded from a single CI channel over a one second period resulting in low numbers of features (i.e. frequency points per band), a classification problem usually solved better by a kNN approach (Eisa et al, 2018). At first, a subject's data was standardized to unit variance and zero mean.…”

Section: Decoding Analysismentioning

confidence: 99%

Direct cochlear recordings in humans show a theta rhythmic modulation of the auditory nerve by selective attention

Gehmacher

Reisinger

Hartmann

et al. 2021

Preprint

View full text Add to dashboard Cite

The architecture of the efferent auditory system enables prioritization of strongly overlapping spatiotemporal cochlear activation patterns elicited by relevant and irrelevant inputs. So far, attempts at finding such attentional modulations of cochlear activity delivered indirect insights in humans or required direct recordings in animals. The extent to which spiral ganglion cells forming the human hearing nerve are sensitive to selective attention remains largely unknown. We investigated this question by testing the effects of attending to either the auditory or visual modality on human hearing nerve activity that was directly recorded with standard commercial MED-EL cochlear implants (CI) during a stimulus-free (anticipatory) cue-target interval. When attending the upcoming auditory input, ongoing hearing nerve activity within the theta range (5-8 Hz) was enhanced. Crucially, using the broadband signal (4-25 Hz), a classifier was even able to decode the attended modality from single-trial data. Follow-up analysis showed that the effect was not driven by a narrow frequency in particular. Using direct cochlear recordings from deaf individuals, our findings suggest that cochlear spiral ganglion cells are sensitive to top-down attentional modulations. Given the putatively broad hair-cell degeneration of these individuals, the effects are likely mediated by alternative efferent pathways as compared to previous studies using otoacoustic emissions. Successful classification of single-trial data could additionally have a significant impact on future closed-loop CI developments that incorporate real-time optimization of CI parameters based on the current mental state of the user.

show abstract

A Comparative Study on using Principle Component Analysis with different Text Classifiers

Cited by 11 publications

References 18 publications

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)

Direct cochlear recordings in humans show a theta rhythmic modulation of the auditory nerve by selective attention

Contact Info

Product

Resources

About