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.

/pdf/using-topic-modeling-methods-for-short-text-data-a-15j608gync.pdf

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

The understanding and analyzing of available content on Social media Platforms such as Twitter and Facebook, through various topic modeling methods is not supervised. However, despite several existing conventional techniques, they have had limited success when applied directly for filtering and quick comprehension of short-text contents due to text sparseness and noise. Thus, it always has been challenging to discover reliable latent topics from online discussion texts that prevail with low words co-occurrence and availability of large size social media benchmark datasets, even for resource-rich languages. The existing literature lacks such work for Urdu text to unveil niche topics even with conventional topic models, mainly due to the lack of benchmark datasets, limited availability of pre-processing tools/ algorithms, and time and compute limitations on large-sized datasets. This work presents experiments with multiple approaches of topic modeling like Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (PLSA), Latent Dirichlet Allocation (LDA), and Non-negative Matrix Factorization (NMF) on 0.8 million Urdu tweets. These tweets are collected through Twitter API by giving various hashtags as a query to avoid dominance of single topic in the dataset. In addition, we have pre-processed the text of the tweets, prepared the three variants of the collected dataset, and extracted multiple features to represent documents on different n-grams. Furthermore, all these techniques are compared and evaluated on the dataset variants, using both qualitative and quantitative measures. We have also demonstrated the results of these approaches through visualization methods, graphs depicting tweets size per topic, word clouds, and hashtags analysis, giving insights about algorithms performances on finalized topics. Observed results reveal that NMF outperformed the techniques with TF-IDF feature vectors in Urdu tweets text, while LDA performed best with merging short-text strategy into long pseudo documents.

/pdf/analyzing-lda-and-nmf-topic-models-for-urdu-tweets-via-2awi7sv98b.pdf

Analyzing LDA and NMF Topic Models for Urdu Tweets via Automatic Labeling

Topic modeling algorithms and applications: A survey

Social media platforms such as (Twitter, Facebook, and Weibo) are being increasingly embraced by individuals, groups, and organizations as a valuable source of information. This social media generated information comes in the form of tweets or posts, and normally characterized as short text, huge, sparse, and low density. Since many real-world applications need semantic interpretation of such short texts, research in Short Text Topic Modeling (STTM) has recently gained a lot of interest to reveal unique and cohesive latent topics. This article examines the current state of the art in STTM algorithms. It presents a comprehensive survey and taxonomy of STTM algorithms for short text topic modelling. The article also includes a qualitative and quantitative study of the STTM algorithms, as well as analyses of the various strengths and drawbacks of STTM techniques. Moreover, a comparative analysis of the topic quality and performance of representative STTM models is presented. The performance evaluation is conducted on two real-world Twitter datasets: the Real-World Pandemic Twitter (RW-Pand-Twitter) dataset and Real-world Cyberbullying Twitter (RW-CB-Twitter) dataset in terms of several metrics such as topic coherence, purity, NMI, and accuracy. Finally, the open challenges and future research directions in this promising field are discussed to highlight the trends of research in STTM. The work presented in this paper is useful for researchers interested in learning state-of-the-art short text topic modelling and researchers focusing on developing new algorithms for short text topic modelling. 

/pdf/short-text-topic-modelling-approaches-in-the-context-of-big-29al33x9.pdf

Short text topic modelling approaches in the context of big data: taxonomy, survey, and analysis

Nowadays, people use online resources such as educational videos and courses. However, such videos and courses are mostly long and thus, summarizing them will be valuable. The video contents (visual, audio, and subtitles) could be analyzed to generate textual summaries, i.e., notes. Videos’ subtitles contain significant information. Therefore, summarizing subtitles is effective to concentrate on the necessary details. Most of the existing studies used Term Frequency–Inverse Document Frequency (TF-IDF) and Latent Semantic Analysis (LSA) models to create lectures’ summaries. This study takes another approach and applies Latent Dirichlet Allocation (LDA), which proved its effectiveness in document summarization. Specifically, the proposed LDA summarization model follows three phases. The first phase aims to prepare the subtitle file for modelling by performing some preprocessing steps, such as removing stop words. In the second phase, the LDA model is trained on subtitles to generate the keywords list used to extract important sentences. Whereas in the third phase, a summary is generated based on the keywords list. The generated summaries by LDA were lengthy; thus, a length enhancement method has been proposed. For the evaluation, the authors developed manual summaries of the existing “EDUVSUM” educational videos dataset. The authors compared the generated summaries with the manual-generated outlines using two methods, (i) Recall-Oriented Understudy for Gisting Evaluation (ROUGE) and (ii) human evaluation. The performance of LDA-based generated summaries outperforms the summaries generated by TF-IDF and LSA. Besides reducing the summaries’ length, the proposed length enhancement method did improve the summaries’ precision rates. Other domains, such as news videos, can apply the proposed method for video summarization. 

Educational Videos Subtitles’ Summarization Using Latent Dirichlet Allocation and Length Enhancement

Text mining is one of the most significant field in the digital era due to the rapid growth of textual information. Topic models are gaining popularity in the last few years. A topic comprises of a group of words that are often take place together. Topic models are better performing techniques to extract semantic knowledge presented in the data. The various methods used for topic models are, LSA (Latent Semantic Analysis), PLSA (Probabilistic Latent Semantic Analysis), LDA (Latent Dirichlet Allocation). These methods gained popularity in extracting hidden themes from the document (corpus). Various topic modeling algorithms are developed to inquiry, summarize and extract hidden semantic structures of large corpus. In this paper, we present a detailed survey covering the various topic modeling techniques proposed in last decade. Additionally, we focus on different strategies of extracting the topics in social media text, where the goal is to find and aggregate the topic within short texts. Further, we summarize the various applications and quantitative evaluation of the various methods, with statistical and mathematical knowledge to predict the convergence of results.

/pdf/a-detailed-survey-on-topic-modeling-for-document-and-short-45v13ejrgx.pdf

A Detailed Survey on Topic Modeling for Document and Short Text Data

Resume screening is a tedious process as it involves a lot of challenges in terms of handling a voluminous number of resumes, performing screening operations, extracting precisely suitable competent profiles out of all available profiles, and so on. In literature several techniques are available for resume screening which include manual inspection, resume parsing, and many more. These techniques produce inconsistent results and consume a lot of time of recruiters as all the techniques lack automation and learning capabilities. This paper uses a 2Q-Learning-based approach enriched with natural language processing capability to accurately evaluate resumes. Additionally, by offering advice on potential resume improvements, it helps to enrich the candidate’s resume. It also eliminates the unconscious prejudice and human errors that occur throughout the traditional recruitment procedure. Overall, it is advantageous for both job seekers and recruiters in terms of learning rate, scalability, and accuracy. Overall, it is advantageous for both job seekers and recruiters.

2Q-Learning Scheme for Resume Screening

Using the Convolutional Neural Network (CNN) algorithm to perform unique classification of skin cancer and evaluating the performance of the SVM approach. n this research work, skin cancer detection has been carried out using algorithms such as CNN and SVM and the accuracy was determined for the same. Two groups are statistically analyzed with the sample size 20 for both the groups, with a pretest g power of 80%. When the CNN algorithm's performance is examined, it is found that the accuracy is 95.03% for CNN and 93.04% for the SVM algorithm. The sample size will be computed using the mean, standard deviation, and standard error, as well as the independent samples test if the significance is less than one. According to the statistical data, the algorithm's accuracy (0.490), specificity (0.009), and p>0.05 significant values are all p0.05. The result shows that CNN algorithm's accuracy was better than SVM algorithm for skin cancer detection.

Skin Cancer Classification using CNN in Comparison with Support Vector Machine for Better Accuracy

The major goal of this research is to segment skin cancer novel images more accurately than Inception V3 using R-CNN (Region-based Convolutional Neural Network). In this research work, Skin cancer detection has been carried out using algorithms such as R-CNN and Inception V3 and the accuracy was determined for the same. Two groups are statistically analysed with the sample size 20 for both the groups, with a pretest g power of 80%. The performance of the R-CNN (Region-based Convolutional Neural Network) algorithm is analysed and it is observed that the accuracy is 96.01% and specificity is 86.76 for R-CNN (Region-based Convolutional Neural Network) and 92.00% and specificity is 89.47 for Inception V3 algorithm. The sample size will be computed using the mean, standard deviation, and standard error, as well as the independent samples test if the significance is less than one. According to the statistical study, the two algorithms' accuracy (0.272) and specificity (0.271) significant values are $\mathbf{p} > 0.05$. In this research, it was observed that the R-CNN performs more accurately than the Inception V3.

Skin Cancer Segmentation Using R-CNN Comparing with Inception V3 for Better Accuracy

Themain aim of this research is to filter Skin Cancer MRI images based on the image processing technologies using novel median filter algorithm and is compared with Gabor filter algorithm. This research contains two groups, each with a sample size of 20 with Gpower of 80 percent. The performance of the novel median filter is evaluated and the performance measurements such as PSNR (Peak Signal to Noise Ratio) and MSE (Mean Square Error) are compared with the Gabor filter. According to the data obtained by simulating with matlab, the novel median filter's PSNR is 31.64, and its MSE is 9.094, whereas the Gabor filter's PSNR (Peak Signal to Noise Ratio) is 27.02, and its MSE (Mean Square Error) is 11.52. From the statistical analysis, it is observed that the significant value of PSNR (Peak Signal to Noise Ratio) (0.409) and $\mathbf{p} > 0.05$ and value of MSE (0.010) of the algorithm is $\mathbf{p} < 0.05$. In this study, it is found that the novel Median filter performs better than the Gabor filter in terms of PSNR and MSE.

S. Likhitha

Papers

A Detailed Survey on Topic Modeling for Document and Short Text Data

2Q-Learning Scheme for Resume Screening

Skin Cancer Classification using CNN in Comparison with Support Vector Machine for Better Accuracy

Skin Cancer Segmentation Using R-CNN Comparing with Inception V3 for Better Accuracy

Performance Analysis of Median Filter in Comparison with Gabor Filter for Skin Cancer MRI Images Based on PSNR and MSE