A multimodal approach to cross-lingual sentiment analysis with ensemble of transformer and LLM.

Sentiment analysis is an essential task in natural language processing that involves identifying a text's polarity, whether it expresses positive, negative, or neutral sentiments. With the growth of social media and the Internet, sentiment analysis has become increasingly important in various fields, such as marketing, politics, and customer service. However, sentiment analysis becomes challenging when dealing with foreign languages, particularly without labelled data for training models. In this study, we propose an ensemble model of transformers and a large language model (LLM) that leverages sentiment analysis of foreign languages by translating them into a base language, English. We used four languages, Arabic, Chinese, French, and Italian, and translated them using two neural machine translation models: LibreTranslate and Google Translate. Sentences were then analyzed for sentiment using an ensemble of pre-trained sentiment analysis models: Twitter-Roberta-Base-Sentiment-Latest, bert-base-multilingual-uncased-sentiment, and GPT-3, which is an LLM from OpenAI. Our experimental results showed that the accuracy of sentiment analysis on translated sentences was over 86% using the proposed model, indicating that foreign language sentiment analysis is possible through translation to English, and the proposed ensemble model works better than the independent pre-trained models and LLM.

An automated materials and processes identification tool for material informatics using deep learning approach.

This article reports a tool that enables Materials Informatics, termed as MatRec, via a deep learning approach. The tool captures data, makes appropriate domain suggestions, extracts various entities such as materials and processes, and helps to establish entity-value relationships. This tool uses keyword extraction, a document similarity index to suggest relevant documents, and a deep learning approach employing Bi-LSTM for entity extraction. For example, materials and processes for electrical charge storage under an electric double layer capacitor (EDLC) mechanism are demonstrated herewith. A knowledge graph approach finds and visualizes different latent knowledge sets from the processed information. The MatRec received an F1 score of 9̃6% for entity extraction, 8̃3% for material-value relationship extraction, and 8̃7% for process-value relationship extraction, respectively. The proposed MatRec could be extended to solve material selection issues for various applications and could be an excellent tool for academia and industry.

Evaluating keyphrase extraction algorithms for finding similar news articles using lexical similarity calculation and semantic relatedness measurement by word embedding.

A textual data processing task that involves the automatic extraction of relevant and salient keyphrases from a document that expresses all the important concepts of the document is called keyphrase extraction. Due to technological advancements, the amount of textual information on the Internet is rapidly increasing as a lot of textual information is processed online in various domains such as offices, news portals, or for research purposes. Given the exponential increase of news articles on the Internet, manually searching for similar news articles by reading the entire news content that matches the user's interests has become a time-consuming and tedious task. Therefore, automatically finding similar news articles can be a significant task in text processing. In this context, keyphrase extraction algorithms can extract information from news articles. However, selecting the most appropriate algorithm is also a problem. Therefore, this study analyzes various supervised and unsupervised keyphrase extraction algorithms, namely KEA, KP-Miner, YAKE, MultipartiteRank, TopicRank, and TeKET, which are used to extract keyphrases from news articles. The extracted keyphrases are used to compute lexical and semantic similarity to find similar news articles. The lexical similarity is calculated using the Cosine and Jaccard similarity techniques. In addition, semantic similarity is calculated using a word embedding technique called Word2Vec in combination with the Cosine similarity measure. The experimental results show that the KP-Miner keyphrase extraction algorithm, together with the Cosine similarity calculation using Word2Vec (Cosine-Word2Vec), outperforms the other combinations of keyphrase extraction algorithms and similarity calculation techniques to find similar news articles. The similar articles identified using KPMiner and the Cosine similarity measure with Word2Vec appear to be relevant to a particular news article and thus show satisfactory performance with a Normalized Discounted Cumulative Gain (NDCG) value of 0.97. This study proposes a method for finding similar news articles that can be used in conjunction with other methods already in use.

Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study.

Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to interpret due to the enormous amount of data necessary to forecast results. For this reason, this study compares eleven machine learning algorithms to determine which one produces the best accuracy for predicting thyroid risk accurately. This study utilizes the Sick-euthyroid dataset, acquired from the University of California, Irvine's machine learning repository, for this purpose. Since the target variable classes in this dataset are mostly one, the accuracy score does not accurately indicate the prediction outcome. Thus, the evaluation metric contains accuracy and recall ratings. Additionally, the F1-score produces a single value that balances the precision and recall when an uneven distribution class exists. Finally, the F1-score is utilized to evaluate the performance of the employed machine learning algorithms as it is one of the most effective output measurements for unbalanced classification problems. The experiment shows that the ANN Classifier with an F1-score of 0.957 outperforms the other nine algorithms in terms of accuracy.