Sentence-level sentiment analysis based on supervised gradual machine learning Scientific Reports

Research conducted on social media data often leverages other auxiliary features to aid detection, such as social behavioral features65,69, user’s profile70,71, or time features72,73. Several methods have been proposed in the existing literature to solve SA tasks, such as supervised and unsupervised machine learning. In SemEval 2014 competition, both Support Vector Machine (SVM) and rule-based machine learning methods were applied. The lexicons were utilized to find the sentiment polarities of reviews using the rule-based technique.

If we take a closer look at the result from each fold, we can also see that the recall for the negative class is quite low around 28~30%, while the precisions for the negative class are high as 61~65%. This means the classifier is very picky and does not think many things are negative. However, it also misses a lot of actual negative class, because it is so very picky. The intuition behind this precision and recall has been taken from a Medium blog post by Andreas Klintberg. The newspaper’s perspective on China’s stability is predominately political and US-centric. The definition of “stability” in China presented in Extract (4) reveals the prevalent understanding in the US that stability means maintaining the CPC’s rule in China, which is thus antithetical to democracy.

In our investigation, this method proved to be time-efficient, verifiable and well-suited to accurately measure the positivity and negativity of sentiments expressed in news discourse. Our future study will utilize this method to compare and examine several large groups of news texts in different periods to uncover hidden sociopolitical factors in them. Besides, this period witnessed China’s consistent domestic and foreign policies, the historic 1997 Hong Kong handover to China, and unprecedented efforts in international image building (Peng, 2004).

Derive useful insights from your data using Python. You will learn both basic and advanced concepts, including text and…

For example, in one study, children were asked to write a story about a time that they had a problem or fought with other people, where researchers then analyzed their personal narrative to detect ASD43. In addition, a case study on Greek poetry of the 20th century was carried out for predicting suicidal tendencies44. …and potentially many other factors have resulted in a vast amount of text data easily accessible to analysts, students, and researchers.

This reduces the computational complexity and memory requirements, making them suitable for large-scale NLP applications. Word embeddings have become a fundamental tool in NLP, providing a foundation for understanding and representing language in a way that aligns with the underlying semantics of words and phrases. This allows models to capture diverse linguistic patterns and assign each word a unique vector, which represents the word’s position in a continuous vector space. Words with similar meanings are positioned close to each other, and the distance and direction between vectors encode the degree of similarity. The Word2Vec model, introduced by Tomas Mikolov and his colleagues at Google in 2013, marked a significant breakthrough.

Support

Within Ethiopia itself, sentiment analysis has been closely linked to political reform. The Ethiopian political landscape has undergone significant changes in recent years, and social media has helped to voice public opinion and influencing political decisions. Social media sites such as Facebook, Twitter, and YouTube were being used to assist in a country’s political reform process. Identifying and categorizing opinions expressed in a piece of text (otherwise known as sentiment analysis) is one of the most performed tasks in NLP. Arabic, despite being one of the most spoken languages of the world, receives little attention as regards sentiment analysis. Therefore this article is dedicated to the implementation of Arabic Sentiment Analysis (ASA) using Python.

It also integrates with modern transformer models like BERT, adding even more flexibility for advanced NLP applications. If the p-value is less than 0.05, we could reject the null hypothesis and conclude that variable X (sentiment) influences stock market changes and volatility. Granger’s test provides insights into how much predictive information one signal has about another one over a given lagged period. Here the p-value measures the statistical significance of the causality between two variables (sentiment and market returns).

The semantic network and word clustering are the external semantic knowledge that aids the prediction of sentiment by the captured semantic relationship. Semantic networks represent the words to convey sentiment, while WordNet exploits the ontological structure. The comparison between supervised and lexicon-based procedures is tabulated in Table 4. The experimental result reveals promising performance gains achieved by the proposed ensemble models compared to established sentiment analysis models like XLM-T and mBERT.

This study delves into the realm of sentiment analysis in the Amharic language, focusing on political sentences extracted from social media platforms in Ethiopia. You can foun additiona information about ai customer service and artificial intelligence and NLP. The research employs deep learning techniques, including Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and a hybrid model combining CNN with Bi-LSTM to analyze and classify sentiments. The hybrid CNN-Bi-LSTM model emerges as the top performer, achieving an impressive accuracy of 91.60%.

These embeddings are based on the idea that the importance or significance of a word can be inferred from how frequently it occurs in the text. Word embeddings generalize well to unseen words or rare words because they learn to represent words based on their context. This is particularly advantageous when working with diverse and evolving vocabularies. GloVe (Global Vectors for Word Representation), introduced by Pennington et al. in 2014, is based on the idea of using global statistics (word co-occurrence frequencies) to learn vector representations for words.

Deep learning and other transfer learning models help to analyze the presence of sentiment in texts. However, when two languages are mixed, the data contains elements of each in a structurally intelligible way. Because code-mixed information does not belong to a single language and is frequently written in Roman script, typical sentiment analysis methods cannot be used to determine its polarity3. Sentiment analysis has been extensively studied at different granularities (e.g., document-level, sentence-level and aspect-level) in the literature. At the document level, the goal is to detect the sentiment polarity of an entire review, which may be composed of multiple sentences.

NLP Cloud’s models thus overcome the complexities of deploying AI models into production while mitigating in-house DevOps and machine learning teams. Finnish startup Lingoes makes a single-click solution to train and deploy multilingual NLP models. It features intelligent text analytics in 109 languages and features automation of all technical steps to set up NLP models. Additionally, the solution integrates with a wide range of apps and processes as well as provides an application programming interface (API) for special integrations. This enables marketing teams to monitor customer sentiments, product teams to analyze customer feedback, and developers to create production-ready multilingual NLP classifiers.

In contrast, stop-word removal entailed the removal of commonly used words such as “and”, “the”, and “in”, which do not contribute to sentiment analysis. While stemming and lemmatization are helpful in some natural language processing tasks, they are generally unnecessary in Transformer-based sentiment analysis, as the models are designed to handle variations in word forms and inflexions. Therefore, stemming and lemmatization were not applied in this study’s data cleaning and pre-processing phase, which utilized a Transformer-based pre-trained model for sentiment analysis.

Emotion and Sentiment Analysis

We obtained a dataset from YouTube; we selected the popular channels and videos related to the Hamas-Israel war that had indicated dataset semantic relevance. Once selected the channel with the video, we used the YouTube API within a script, such as Google Apps Script, to fetch the desired pieces of comments on the video by adding a video ID on the Google Sheets. Therefore, the script makes requests to the API to retrieve video metadata ChatGPT App about that video and store this comment in a dataset format, such as a CSV file or a Google Sheet. Therefore, we downloaded the prepared data from Google Sheets which consists of CNN of 2462, Aljazeera 4570, Reuters 6846, BBC of 2050, and WION of 8432, which we then annotated by linguistic experts as positive, negative, or neutral, respectively. As a result, Table 1 depicts the labeled dataset distribution per proposed class.

• Hence, semantic search models find applications in areas such as eCommerce, academic research, enterprise knowledge management, and more.
• Hence, all the mentioned algorithms are unsupervised, so there is no need for human input or training corpus.
• The current study selects six of the most frequent semantic roles for in-depth investigation, including three core arguments (A0, A1, and A2) and three semantic adjuncts (ADV, MNR, and DIS).
• Confusion matrix of adapter-BERT for sentiment analysis and offensive language identification.

The Continuous Skip-gram model, on the other hand, takes a target word as input and aims to predict the surrounding context words. Below are some of the key concepts and developments that have made using word embeddings such a powerful technique in helping advance NLP. Actual word embeddings semantic analysis of text typically have hundreds of dimensions to capture more intricate relationships and nuances in meaning. Word embeddings can be used to perform word similarity tasks (e.g., finding words similar to a given word) and word analogy tasks (e.g., “king” is to “queen” as “man” is to “woman”).

• It also supports custom entity recognition, enabling users to train it to detect specific terms relevant to their industry or business.
• Latvian startup SummarizeBot develops a blockchain-based platform to extract, structure, and analyze text.
• • NMF is an unsupervised matrix factorization (linear algebraic) method that is able to perform both dimension reduction and clustering simultaneously (Berry and Browne, 2005; Kim et al., 2014).

CNN works well in long-range semantic comprehension and detects the local and position-defined pattern. The model generates a feature map of sentences by using k-max-pooling to obtain the short and long relationship between words and phrases. Capsule neural network (CapsNets) view the capsule as a group of neurons that have different attributes of an entity.

While the study focused on laptops, phones, and televisions, there’s room for extending this approach to different products and languages in future research. Several researchers have ChatGPT endeavored to build sentiment classification models for Amharic. Abraham6 applied machine learning to Amharic entertainment texts, achieving 90.9% accuracy using Naïve Bayes.