Sentiment analysis of the Hamas-Israel war on YouTube comments using deep learning Scientific Reports

Its scalability and speed optimization stand out, making it suitable for complex tasks. Natural language processing (NLP) is a field within artificial intelligence that enables computers to interpret and understand human language. Using machine learning and AI, NLP tools analyze text or speech to identify context, meaning, and patterns, allowing computers to process language much like humans do. One of the key benefits of NLP is that it enables users to engage with computer systems through regular, conversational language—meaning no advanced computing or coding knowledge is needed.

The actual sentiment labels of reviews are shown by green (positive) and red (negative). It is evident from the plot that most mislabeling happens close to the decision boundary as expected. To solve this issue, I suppose that the similarity of a single word to a document equals the average of its similarity to the top_n most similar words of the text. Then I will calculate this similarity for every word in my positive and negative sets and average over to get the positive and negative scores. To put it differently, to estimate the positive score for a review, I calculate the similarity of every word in the positive set with all the words in the review, and keep the top_n highest scores for each positive word and then average over all the kept scores. Released to the public by Stanford University, this dataset is a collection of 50,000 reviews from IMDB that contains an even number of positive and negative reviews with no more than 30 reviews per movie.

The overall polarity of the review was computed by summing the polarity scores of all words in the review and dividing by their distance from the aspect term. If a sentence’s polarity score is less than zero (0), it is classified as negative; if the score is equal to zero, it is defined as neutral; and if the score is equal to or more than one, it is defined as positive. These classified features and n-gram features have been used to train machine learning algorithms.

Stochastic gradient descent (SGD) and K-nearest neighbour (KNN) and had performed, followed by LR, which has 66.7% and 63.6% of accuracy. For the second model, the dataset consists of 65 instances with the label ‘Physical’ and 43 instances with the label ‘Non-physical. The feature engineering technique, the Term Frequency/ Inverse Document Frequency (TFIDF) is applied. After that, the Principal Component Analysis (PCA) is applied for dimensionality reduction. The 108 instances are then split into train dataset and test dataset, where 30% of the dataset is used for testing the performance of the model.

They build several machine learning classifiers and deep learning classifiers using the neural network LSTM and GRU. Some machine classification technique was introduced and tabulated in Table 1. Rocchio classification uses the frequency of the words from a vector and compares the similarity of that vector and a predefined prototype vector. This classification is not general because it is limited to retrieving a few relevant documents.

LR algorithms achieve the highest accuracy out of all others machine learning and deep learning algorithms. In the cited paper, sentiment analysis of Arabic text ChatGPT App was performed using pre-trained word embeddings. Recently, pre-trained algorithms have shown the state of the art results on NLP-related tasks27,28,29,30.

Step 3. Use the best social media sentiment analysis tool

Rules are established on a comment level with individual words given a positive or negative score. If the total number of positive words exceeds negative words, the text might be given a positive sentiment and vice versa. You then use sentiment analysis tools to determine how customers feel about your products or services, customer service, and advertisements, for example. Sentiment analysis, or opinion mining, analyzes qualitative customer feedback (often written language) to determine whether it contains positive, negative, or neutral emotions about a given subject. And, since sentiment is often shared through online platforms like ecommerce sites, social media, and digital accounts, you can use those channels to access a deeper, almost intuitive understanding of customer desires and behaviors. The next step involves combining the predictions furnished by the BERT, RoBERTa, and GPT-3 models through a process known as majority voting.

The numbers in the table represent the forecasting error of each model with respect to the AR(2) forecasting error. We used the Diebold-Mariano test66 to determine if the forecasting errors of each model were statistically worse (in italic) than the best model, whose RMSFEs are highlighted in bold. The Granger causality tests for sentiment indicate significance only for the second question, which pertains to the assessment semantic analysis of text of the household’s economic situation. In line with the findings presented in Table 2, it appears that ERKs have a greater influence on current assessments than on future projections. This is aligned with the current debate in the literature on consumer confidence, as it is still unclear whether surveys merely reflect current or past events or provide useful information about the future of household spending8.

The hybrid architectures avail from the outstanding characteristic of each network type to empower the model. This section explains the details of the proposed set of machine learning, rule-based, a set of deep learning algorithms and proposed mBERT model. The set of machine learning algorithms such as KNN, RF, NB, LR, MLP, SVM, and AdaBoost are used to classify Urdu reviews.

A distribution on topics is first sampled from a Dirichlet distribution, and a topic is further chosen based on this distribution. Moreover, each document is modeled as a distribution over topics, and a topic is represented as a distribution over words. Another challenge when translating foreign language text for sentiment analysis is the idiomatic expressions and other language-specific attributes that may elude accurate capture by translation tools or human translators43. You can foun additiona information about ai customer service and artificial intelligence and NLP. One of the primary challenges encountered in foreign language sentiment analysis is accuracy in the translation process. Machine translation systems often fail to capture the intricate nuances of the target language, resulting in erroneous translations that subsequently affect the precision of sentiment analysis outcomes39,40.

“Performance evaluation of topic modeling algorithms for text classification,” in rd International Conference on Trends in Electronics and Informatics (ICOEI) (Tirunelveli). • R TM packages include three packages that are capable of doing topic modeling analysis which are MALLET, topic models, and LDA. Also, the R language has many packages and libraries for effective topic modeling like LSA, LSAfun (Wild, 2015), topicmodels (Chang, 2015), and textmineR (Thomas Jones, 2019).

In terms of syntactic subsumption, it seems that CT have an inclination for simplification in argument structure. Moreover, the average number of argument structures in Chinese sentences should be bigger than that in English sentences since they have a similar average number of semantic roles in a sentence. The distinctive aspect of our textual entailment analysis is that we take a given sentence as H and create its T by changing the predicate in the sentence into its root hypernym. In this way we manually create a determined entailment relationship between T and H. Based on this methodology, the extra information I(E) in Formula (1) can be approximated by the distance between the original predicate and its root hypernym. Then the distance can be quantified as 1 minus the Wu-Palmer Similarity or Lin Similarity between the original predicate and its root hypernym.

Study 1

Specifically, the authors used a pre-trained multilingual transformer model to translate non-English tweets into English. They then used these translated tweets as additional training data for the sentiment analysis model. This simple technique allows for taking advantage of multilingual models for non-English tweet datasets of limited size. Sentiment analysis, the computational task of determining the emotional tone within a text, has evolved as a critical subfield of natural language processing (NLP) over the past decades1,2. It systematically analyzes textual content to determine whether it conveys positive, negative, or neutral sentiments. This capability holds immense importance in understanding public opinion, customer feedback, and social discourse, making it a fundamental principle in various applications across fields such as marketing, politics, and customer service3,4,5.

Moreover, researchers have sought to supplement their findings by examining evidence from alternative sources such as literary texts and life writings. Consequently, the task of extracting specific content from extensive texts like novels is arduous and time-consuming. The scholarly community has made substantial progress in comprehending the multifaceted nature of sexual harassment cases in the Middle East (Karami et al., 2021).

• In addition, the Bi-GRU-CNN trained on the hyprid dataset identified 76% of the BRAD test set.
• For instance, we may use consumer surveys in conjunction with our methods to gain a more comprehensive understanding of the market.
• The Continuous Skip-gram model uses training data to predict the context words based on the target word’s embedding.
• This section will guide you through four steps to conduct a thorough social sentiment analysis, helping you transform raw data into actionable strategies.
• In the above example, the translation follows the information structure of the source text and retains the long attribute instead of dividing it into another clause structure.

Through a granular analysis of the dimensions of consumer confidence, we found that the extent to which the news impacts consumers’ economic perception changes if we consider people’s current versus prospective judgments. Our forecasting results demonstrate that the SBS indicator predicts most consumer perception categories more than the language sentiment expressed in the articles. ERKs seem to impact more the Personal climate, i.e., consumers’ perception of their current ability to save, purchase durable assets, and feel economically stable. In addition, we find a disconnect between the ERKs’ impact on the current and future assessments of the economy, which is aligned with other studies68,69.

The bias of machine learning models stems from the data preparation phase, where a rule-based algorithm is employed to identify instances of sexual harassment. The accuracy of this process heavily relies on the collection of sexual harassment words used to detect such sentences, thereby influencing the final outcome. Consequently, it becomes imperative to incorporate manual interpretation in order to review and validate the selection of sexual harassment sentences. However, it is important to acknowledge that both manual annotation and computational modelling introduce systematic errors that can lead to bias. To mitigate these defects, a few domain experts should be involved in the manual interpretation process to ensure a more reliable result.

Examples of Semantic Analysis

Semantic analysis methods will provide companies the ability to understand the meaning of the text and achieve comprehension and communication levels that are at par with humans. Thus, as and when a new change is introduced on the Uber app, the semantic analysis algorithms start listening to social network feeds to understand whether users are happy about the update or if it needs further refinement. Moreover, granular insights derived from the text allow teams to identify the areas with loopholes and work on their improvement on priority.

Subsequently, data preparation, modelling, evaluation, and visualization phases were conducted for each model in order to assess their performance. 1 and provides an overview of the entire process, from data pre-processing to visualization. Furthermore, this framework can be used as a reference for future studies on sexual harassment classification. There are three types of procedures, which are supervised method, lexicon-based method, and semantic based method.

Another critical consideration in translating foreign language text for sentiment analysis pertains to the influence of cultural variations on sentiment expression. Diverse cultures exhibit distinct conventions in conveying positive or negative emotions, posing challenges for accurate sentiment capture by translation tools or human translators41,42. The work described in12 focuses on scrutinizing the preservation of sentiment through machine translation processes. To this end, a sentiment gold standard corpus featuring annotations from native financial experts was curated in English. The first objective was to assess the overall translation quality using the BLEU algorithm as a benchmark. The second experiment identified which machine translation engines most effectively preserved sentiments.

Bi-LSTM, in contrast to LSTM, contains forward and backward layers for conducting additional feature extractions which is suitable for Amharic language because the language by its nature needs context information to understand the sentence. One copy of the hidden layer fits in the input sequences as the traditional LSTM, while the other is placed on a reversed copy of the input sequence. For both the forward and backward hidden layers in our model, the researcher used a bidirectional LSTM with a 64-memory unit. Then add a dropout of (0.4, 0.5), Random state of 50, Embedded size of 32, batch size of 100, and 3 epochs to minimize overfitting. To calculate the loss function Binary Classification were used and Adam as an optimizer.

An RNN network was trained using feature vectors computed using word weights and other features as percentage of positive, negative and neutral words. RNN, SVM, and L2 Logistic Regression classifiers were tested and compared using six datasets. In addition, LSTM models were widely applied for Arabic SA using word features and applying shallow structures composed of one or two layers15,40,41,42, as shown in Table 1. Meltwater’s latest sentiment analysis model incorporates features such as attention mechanisms, sentence-based embeddings, sentiment override, and more robust reporting tools. With these upgraded features, you can access the highest accuracy scores in the field of natural language processing. However, with advancements in linguistic theory, machine learning, and NLP techniques, especially the availability of large-scale training corpora (Shao et al., 2012), SRL tools have developed rapidly to suit technical and operational requirements.

By adapting Plutchik’s taxonomy (Fig. 1), we can fit the emotions to the Fear and Greed Index, and thus grade them in terms of their relation to being more or less prone to risk aversion or risk attraction. Incidentally, rational choice theory in economics, as the best-established theory on investment behaviour, considers that individuals react predictably and rationally in terms of economic or financial decisions (Zey, 1998). We can also group by the entity types to get a sense of what types of entites occur most in our news corpus. Besides these four major categories of parts of speech , there are other categories that occur frequently in the English language. These include pronouns, prepositions, interjections, conjunctions, determiners, and many others.

Word embeddings have become integral to tasks such as text classification, sentiment analysis, machine translation and more. BERT is a pre-trained language model that has been shown to be very effective for a variety of NLP tasks, including sentiment analysis. BERT is a deep learning model that is trained on a massive dataset of text and code. This training allows BERT to learn the contextual relationships between words and phrases, which is essential for accurate sentiment analysis. Emotion-based sentiment analysis goes beyond positive or negative emotions, interpreting emotions like anger, joy, sadness, etc. Machine and deep learning algorithms usually use lexicons (a list of words or phrases) to detect emotions.

It utilizes natural language processing techniques such as topic clustering, NER, and sentiment reporting. Companies use the startup’s solution to discover anomalies and monitor key trends from customer data. The architecture of RNNs allows previous outputs to be used as inputs, which is beneficial when using sequential data such as text.

Furthermore, each POS tag like the noun (N) can be further subdivided into categories like singular nouns (NN), singular proper nouns (NNP), and plural nouns (NNS). You can see that the semantics of the words are not affected by this, yet our text is still standardized. Lemmatization is very similar to stemming, where we remove word affixes to get to the base form of a word. However, the base form in this case is known as the root word, but not the root stem.

• To identify the most suitable models for predicting sexual harassment types in this context, various machine learning techniques were employed.
• To calculate the loss function Binary Classification were used and Adam as an optimizer.
• Word stems are also known as the base form of a word, and we can create new words by attaching affixes to them in a process known as inflection.
• Furthermore, Sawhney et al. introduced the PHASE model166, which learns the chronological emotional progression of a user by a new time-sensitive emotion LSTM and also Hyperbolic Graph Convolution Networks167.

Their extensive testing indicates that this model sets a new benchmark, surpassing previous state-of-the-art methods52,53. This study presents two models that have been developed to address the issue of sexual harassment. The first model is a machine learning model which is capable of accurately classifying different types of sexual harassment. The second model, which leverages a deep learning approach, is used to classify sentiment and emotion. To ensure the accuracy of the models, a comprehensive text pre-processing process was applied to the text data.

In semantic analysis, relationships include various entities, such as an individual’s name, place, company, designation, etc. Moreover, semantic categories such as, ‘is the chairman of,’ ‘main ChatGPT branch located a’’, ‘stays at,’ and others connect the above entities. Users can download pre-trained GloVe embeddings and fine-tune them for specific applications or use them directly.

If your company doesn’t have the budget or team to set up your own sentiment analysis solution, third-party tools like Idiomatic provide pre-trained models you can tweak to match your data. These graphical representations serve as a valuable resource for understanding how different combinations of translators and sentiment analyzer models influence sentiment analysis performance. Following the presentation of the overall experimental results, the language-specific experimental findings are delineated and discussed in detail below.

CNN predicts 1904 correctly identified positive comments in sentiment analysis and 2707 correctly identified positive comments in offensive language identification. Logistic regression is a classification technique and it is far more straightforward to apply than other approaches, specifically in the area of machine learning. The character vocabulary includes all characters found in the dataset (Arabic characters, , Arabic numbers, English characters, English numbers, emoji, emoticons, and special symbols). CNN, LSTM, GRU, Bi-LSTM, and Bi-GRU layers are trained on CUDA11 and CUDNN10 for acceleration. Combinations of word embedding and handcrafted features were investigated for sarcastic text categorization54. Sarcasm was identified using topic supported word embedding (LDA2Vec) and evaluated against multiple word embedding such as GloVe, Word2vec, and FastText.