Text Representation for Sentiment Analysis: From Static to Dynamic

Sentiment Analysis is an important research direction of natural language processing, and it is widely used in politics, news and other fields. Word embeddings play a significant role in sentiment analysis. The existing sentiment embeddings methods directly embed the sentiment lexicons into traditional word representation. This sentiment representation methods can only differentiate the sentiment information of different words, not the same word in different contexts, so it cannot provide accurate sentiment information for word in different contexts. This paper proposes sentiment concept to solve the problem. First, we found the optimal sentiment concept of words in Microsoft Concept Graph according to the context of words. Then we obtained the sentiment information of words under optimal sentiment concept from the multi-semantics sentiment intensity lexicon which we constructed in this paper to achieve accurate embedding of sentiment information and provide more accurate semantics and sentiment representation for words. Finally, we combined two refined word embeddings methods to achieve a more comprehensive word representation. Compared with traditional and sentiment embeddings methods on six representative datasets, the validity of the word embeddings method based on sentiment concept proposed in this paper is verified.

At least since the invention of writing, people have been troubled by the problem of what a word means. Dictionaries have traditionally been written with numbered word senses, giving the impression that the different senses of a word are fixed abstract entities, which can be used to separate usages into neat piles according to their different meanings. Adam Kilgarriff’s daring 1997 article ‘I Don’t Believe in Word Senses’ challenged this traditional view of word meaning, presenting an account in which ‘the basic units are occurrences of the word in context’. Kilgarriff went on to develop the Sketch Engine, a statistical tool that enables lexicographers and NLP researchers, teachers, and students to explore the relationship between meanings and collocations (words and their contexts). In this review article, we compare the information provided by Kilgarriff’s Word Sketches with the recently developed Word Embedding techniques and with the results of Corpus Pattern Analysis.

Interpretability of word vector components is very important for obtaining conceptual relations. Word vectors derived from counting models are interpretable but suffer from the high-dimensionality problem. Our goal in this study is to obtain interpretable low-dimensional word vectors in such a way that the least accuracy loss occurs. To achieve this goal, we propose an approach to reduce the dimensions of word vectors using a labeling method based on the BPSO algorithm and a voting method for selecting final context words. In this approach, we define several different base models to solve the labeling problem using different data and different objective functions. Then, we train each base model and select 3 of the best solutions for each model. We create the target word vectors of the dictionary based on the context words labeled 1. Next, we use the three best solutions of each base model to build the ensemble. After creating the ensemble, we use the voting method to assign the final label to the primary context words and select N final context words. In this study, we use the corpus ukWaC to construct word vectors. We evaluate the resulting word vectors on the MEN, RG-65, and SimLex-999 test sets. The evaluation results show that by reducing the word vectors dimensions from 5000 to 1507, the Spearman correlation coefficient of the proposed approach has been reduced to a lesser extent compared to each base model. Therefore, the accuracy drop of the proposed approach is justified after reducing the dimensions from 5000 to 1507. It is not a large penalty because the resulting word vectors are low-dimensional and interpretable.

Attention-based position-aware framework for aspect-based opinion mining using bidirectional long short-term memory

Detecting spam emails is essential to maintaining the security and integrity of email communication. Existing research has made significant progress in developing effective spam detection models, but challenges remain in improving classification performance and adaptability to evolving spamming techniques. In this study, we propose a novel spam detection model with a comprehensive feature engineering approach that combines term frequency-inverse document frequency (TF-IDF) vectorizer and word embedding features to optimize the feature space. Our contribution lies in integrating semantic-based word embeddings, leveraging pre-existing knowledge to capture the semantic meaning of words and enhance the representation of email texts. To identify the most suitable word embedding technique for our model, we evaluated GloVe, Word2Vec, and FastText. GloVe was selected for its better performance, which is the result of its pre-training on a large and diverse text corpus. Furthermore, the model was evaluated without word embeddings, which did not exhibit the same effectiveness level as our word embedding-based model. Additionally, we utilized the support vector machine as a classifier and hyperparameter tuning technique to identify our model’s most effective parameter values. The proposed model was tested on two datasets. The experimental results showed that our model outperformed the other models discussed in the literature, achieving an accuracy of 99.5% on the SpamAssassin dataset, and 99.28% on the Enron-Spam dataset.

The sentiment analysis of microblog text has always been a challenging research field due to the limited and complex contextual information. However, most of the existing sentiment analysis methods for microblogs focus on classifying the polarity of emotional keywords while ignoring the transition or progressive impact of words in different positions in the Chinese syntactic structure on global sentiment, as well as the utilization of emojis. To this end, we propose the emotion-semantic-enhanced bidirectional long short-term memory (BiLSTM) network with the multi-head attention mechanism model (EBILSTM-MH) for sentiment analysis. This model uses BiLSTM to learn feature representation of input texts, given the word embedding. Subsequently, the attention mechanism is used to assign the attentive weights of each words to the sentiment analysis based on the impact of emojis. The attentive weights can be combined with the output of the hidden layer to obtain the feature representation of posts. Finally, the sentiment polarity of microblog can be obtained through the dense connection layer. The experimental results show the feasibility of our proposed model on microblog sentiment analysis when compared with other baseline models.

Textual representation learners trained on large amounts of data have achieved notable success on downstream tasks; intriguingly, they have also performed well on challenging tests of syntactic competence. Hence, it remains an open question whether scalable learners like BERT can become fully proficient in the syntax of natural language by virtue of data scale alone, or whether they still benefit from more explicit syntactic biases. To answer this question, we introduce a knowledge distillation strategy for injecting syntactic biases into BERT pretraining, by distilling the syntactically informative predictions of a hierarchical—albeit harder to scale—syntactic language model. Since BERT models masked words in bidirectional context, we propose to distill the approximate marginal distribution over words in context from the syntactic LM. Our approach reduces relative error by 2–21% on a diverse set of structured prediction tasks, although we obtain mixed results on the GLUE benchmark. Our findings demonstrate the benefits of syntactic biases, even for representation learners that exploit large amounts of data, and contribute to a better understanding of where syntactic biases are helpful in benchmarks of natural language understanding.

Sentiment analysis refers to the automated process of identifying the underlying emotional tone conveyed in a text. This task has become increasingly crucial today due to the exponential growth of opinion-oriented text generation on various online platforms including social media and e-commerce websites. The process of sentiment analysis has evolved through different phases like the use of handcrafted rules, sentiment-oriented dictionaries, machine learning, deep learning, transformer models, and large language models. These different phases have enriched the field of sentiment analysis and enabled it to get better insights into text for sentiment analysis. One of the most impactful developments in sentiment analysis was the creation of embedding’s for words or sentences, which are useful for representing unstructured data as structured data. These embedding are representing words or sentences as numerical vectors in a high-dimensional space and have proven effective in capturing the semantic relationships between words. By leveraging the power of embedding’s, sentiment analysis models can understand the complexities of human language and provide more precise insights into people's emotions and opinions. However, word embedding’s not inherently generated for sentiment analysis, which means that they are not inherently sentiment-oriented. Therefore, many researchers have focused on developing sentiment-oriented word embedding’s for sentiment words, but they have overlooked the importance of intensity words such as “little”, “high”, and “extremely”. These intensity words determine the level of sentiment expressed in text, which is particularly useful for fine-level sentiment analysis. To address this issue, a review proposes an intensity-aware word embedding development model and sentiment analysis with ML.

Word embeddings are widely used in Natural Language Processing (NLP) for a vast range of applications. However, it has been consistently proven that these embeddings reflect the same human biases that exist in the data used to train them. Most of the introduced bias indicators to reveal word embeddings’ bias are average-based indicators based on the cosine similarity measure. In this study, we examine the impacts of different similarity measures as well as other descriptive techniques than averaging in measuring the biases of contextual and non-contextual word embeddings. We show that the extent of revealed biases in word embeddings depends on the descriptive statistics and similarity measures used to measure the bias. We found that over the ten categories of word embedding association tests, Mahalanobis distance reveals the smallest bias, and Euclidean distance reveals the largest bias in word embeddings. In addition, the contextual models reveal less severe biases than the non-contextual word embedding models.

In this paper we compare structure of Czech word embeddings for English-Czech neural machine translation (NMT), word2vec and sentiment analysis. We show that although it is possible to successfully predict part of speech (POS) tags from word embeddings of word2vec and various translation models, not all of the embedding spaces show the same structure. The information about POS is present in word2vec embeddings, but the high degree of organization by POS in the NMT decoder suggests that this information is more important for machine translation and therefore the NMT model represents it in more direct way. Our method is based on correlation of principal component analysis (PCA) dimensions with categorical linguistic data. We also show that further examining histograms of classes along the principal component is important to understand the structure of representation of information in embeddings.

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated by a hidden semantic vector encoding its contextual semantic meaning, and its context words are generated conditional on both the hidden semantic vector and global latent topics. Topics are trained jointly with the word embeddings. The trained model maps words to topic-dependent embeddings, which naturally addresses the issue of word polysemy. Experimental results show that the proposed model outperforms the word-level embedding methods in both word similarity evaluation and word sense disambiguation. Furthermore, the model also extracts more coherent topics compared with existing neural topic models or other models for joint learning of topics and word embeddings. Finally, the model can be easily integrated with existing deep contextualized word embedding learning methods to further improve the performance of downstream tasks such as sentiment classification.

Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered as an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence. This is basically used in application like information retrieval, machine translation, information extraction because of its semantics understanding. This paper describes the proposed approach (WSD-TIC) which is based on the words surrounding the polysemous word in a context. Each meaning of these words is represented by a vector composed of weighted nouns using taxonomic information content. The main emphasis of this paper is feature selection for disambiguation purpose. The assessment of WSD systems is discussed in the context of the Senseval campaign, aiming at the objective evaluation of our proposal to the systems participating in several different disambiguation tasks.

Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered as a task whose solution is at least as hard as the most difficult problems in artificial intelligence. This is basically used in application like information retrieval, machine translation, information extraction because of its semantics understanding. This paper describes the proposed approach W3SD (This paper is an extended version of our work [4] published in the 8th International Conference on Computational Collective Intelligence.) which is based on the words surrounding the polysemous word in a context. Each meaning of these words is represented by a vector composed of weighted nouns using WordNet and Wiktionary features through the taxonomic information content from WordNet and the glosses from Wiktionary. The main emphasis of this paper is feature selection for disambiguation purpose. The assessment of WSD systems is discussed in the context of the Senseval campaign, aiming at the objective evaluation of our proposal to the systems participating in several different disambiguation tasks.

Word embeddings, the coefficients from neural network models predicting the use of words in context, have now become inescapable in applications involving natural language processing. Despite a few studies in political science, the potential of this methodology for the analysis of political texts has yet to be fully uncovered. This paper introduces models of word embeddings augmented with political metadata and trained on large-scale parliamentary corpora from Britain, Canada, and the United States. We fit these models with indicator variables of the party affiliation of members of parliament, which we refer to as party embeddings. We illustrate how these embeddings can be used to produce scaling estimates of ideological placement and other quantities of interest for political research. To validate the methodology, we assess our results against indicators from the Comparative Manifestos Project, surveys of experts, and measures based on roll-call votes. Our findings suggest that party embeddings are successful at capturing latent concepts such as ideology, and the approach provides researchers with an integrated framework for studying political language.

Word embeddings are essential to natural language processing tasks because they contain a single word’s syntactic and semantic information. Word embeddings have been developed widely for numerous spoken languages across the globe like English. The research community needs to pay more attention to the Urdu language despite its significant number of speakers, which amounts to approximately 231.3 million individuals. Urdu is a complex language because word boundaries in Urdu are unspecified, as it does not employ delimiters between words. The compound word, a multiword expression, is a more complex word consisting of many strings or independent base words. Traditionally, compound words are identified during the word segmentation using bigram or trigram approaches. The challenge with these techniques is that they do not produce meaningful words. This study uses morphological rule-based compound words in Urdu text documents. For text representation, a self-trained morphological rule-based compound word embedding (Cword2vec) based on the word2vec model is proposed for Urdu text sentiment analysis. The performance of self-trained morphological rule-based compound word embedding was then evaluated using four well-known deep learning models, i.e., long short-term memory (LSTM), bidirectional LSTM (BiLSTM), convolutional neural networks (CNN), and convolutional LSTM (C-LSTM) for sentiment analysis. We also compare the performance of morphological rule-based compound words with traditional compound word identification techniques such as bigrams and trigrams. Regardless of the classification model, word embedding using our proposed morphological rule-based compound words outperformed in terms of precision, recall, F1 score, and accuracy than bigrams and trigrams.