Lexicon Approach Research Articles

Comparative Analysis of Lexicon and Machine Learning Approach for Sentiment Analysis

Opinion mining or analysis of text are other terms for sentiment analysis. The fundamental objective is to extract meaningful information and data from unstructured text using natural language processing, statistical, and linguistics methodologies. This further is used for deriving qualitative and quantitative results on the scale of ‘positive’, ‘neutral’, or ‘negative to get the overall sentiment analysis. In this research, we worked with both approaches, machine learning, and an unsupervised lexicon-based algorithm for sentiment calculation and model performance. Stochastic gradient descent (SGD) is utilized in this work for optimization for support vector machine (SVM) and logistic regression. AFINN and Vader lexicon are used for the lexicon model. Both the feature TF-IDF and bag of a word are used for classification. This dataset includes "Trip advisor hotel reviews". There are around 20k reviews in the dataset. Cleaned and preprocessed data were used in our work. We conducted some training and assessment. A classifier's accuracy is measured using evaluation metrics. In TF-IDF, the Support Vector Machine is the more accurate of the two classifiers used to assess machine learning accuracy. The classification rate in Bag of Words was 95.2 percent and the accuracy in TF-IDF was 96.3 percent on the support vector machine algorithm. VADER outperforms the Lexicon model with an accuracy of 88.7%, whereas AFINN Lexicon has an accuracy of 86.0%. When comparing the Supervised and unsupervised lexicon approaches, support vector machine model outperforms with a TFIDF accuracy of 96.3 percent and a VADER lexicon accuracy of 88.7%.

Detecting Aggressiveness in Tweets: A Hybrid Model for Detecting Cyberbullying in the Spanish Language

In recent years, the use of social networks has increased exponentially, which has led to a significant increase in cyberbullying. Currently, in the field of Computer Science, research has been made on how to detect aggressiveness in texts, which is a prelude to detecting cyberbullying. In this field, the main work has been done for English language texts, mainly using Machine Learning (ML) approaches, Lexicon approaches to a lesser extent, and very few works using hybrid approaches. In these, Lexicons and Machine Learning algorithms are used, such as counting the number of bad words in a sentence using a Lexicon of bad words, which serves as an input feature for classification algorithms. This research aims at contributing towards detecting aggressiveness in Spanish language texts by creating different models that combine the Lexicons and ML approach. Twenty-two models that combine techniques and algorithms from both approaches are proposed, and for their application, certain hyperparameters are adjusted in the training datasets of the corpora, to obtain the best results in the test datasets. Three Spanish language corpora are used in the evaluation: Chilean, Mexican, and Chilean-Mexican corpora. The results indicate that hybrid models obtain the best results in the 3 corpora, over implemented models that do not use Lexicons. This shows that by mixing approaches, aggressiveness detection improves. Finally, a web application is developed that gives applicability to each model by classifying tweets, allowing evaluating the performance of models with external corpus and receiving feedback on the prediction of each one for future research. In addition, an API is available that can be integrated into technological tools for parental control, online plugins for writing analysis in social networks, and educational tools, among others.

Stage Performance and Musical Analysis of Haacaaluu Hundeessaa Works by using Sentiment Analysis Techniques

This research is initiated to analysis the stage performance and musical analysis of Haacaaluu Hundeessaa works on Afaan oromoo reviews text collected from social Medias by applying the concept of sentiment analysis techniques. The data (reviews) were collected manually from social media on Haacaaluu Hundeessaa musical works. Haacaaluu Hundeessaa is Oromo singer, songwriter, civil rights activist and his being a voice his people. He is the most famous young singer, hero and icon of Oromo musician. From his musical works Sanyii Mootii(Race of the King), Waa'ee Keenyaa(Our Plight), Maalan Jira(What existence is mine), JIRTUU? are the most popular known in Oromo peoples as well as nation and nationality of Ethiopia. From Hacaaluu musical works, the researcher considered reviews (opinions) afaan oromoo text data on his single sang “JIRTUU?” to analysis stage performance of Haacaaluu Hundeessaa’s. The researcher inspires to use this single sang because; reviews (comments) are easier to access, available on you tube channel, extensive in size relatively from other his songs from social media. Additionally this song was broadcast live by Oromia Broadcasting Network and other Medias on different stage. Opinion lexicon approach with contextual valence shifter is used for analyzing opinions (comments) given on stage performance of Haacaaluu Hundeessaa works. Totally 18,687 reviews opinions or sentences were collected for experimentations to analysis stage performance and musical works of Haacaaluu Hundeessaa. Accordingly our result indicates around 99.52 percents peoples likes the stage performance and musical works of Hacaaluu Hundeessaa. From the results researcher observed Haacaaluu Hundeessaa has good performer with sing emotional and physically when he sing on the stages. In future works, further research needs to study others musical works of Hacaaluu Hundeessaa.

STAYING IN THEIR LANES: ISSUE OWNERSHIP IN THE 2016 AND 2020 U.S. PRESIDENTIAL CAMPAIGNS ON FACEBOOK AND TWITTER

Prior research has identified issue-ownership across partisan lines, with Republicans seen to focus on issues such as taxes and national defense, and Democrats more likely to focus on social issues and welfare. Given the complexities of the primary race, with candidates aiming to differentiate themselves within their own party, we ask whether the candidates in both parties engage in creating “lanes” by owning specific policy topics. Use supervised machine-learning and a lexicon approach to classify candidate posts on twelve different political topics, we analyze Facebook and Twitter messages from 17 Republicans and 19 Democrats during the 2016 and 2020 U.S. Presidential Elections. We find that Democrats are more likely to post about the issues on social media, and Republicans and Democrats talk about significantly different topics. We also find that candidates of both parties tended to advocate for the issues they cared about, rather than attack opponents on issues.

A FrontPage Online News Analysis: An Opinion Mining Approach

The advent of the internet with its attendant democratization of data and deluge of information had given rise to the avalanche of news media agencies. These agencies publish news articles with varying emotional reports especially stories conveying bad sentiments to the public. As major news agencies operate micro-blogging websites and establish their presence on social media channels, the distribution of bad news increases. It has been shown that constant exposure to bad news presented in a body of texts, graphics, and videos/audios contribute to increase in high blood pressure, anxiety attacks, bowel disorders, stroke and/or heart failure. In this work, we presented a sentiment analysis framework to extract news articles from FrontPage of online newspapers and generate contextual wordlists to support positive news broadcasting. Using a set of 12 Nigerian online news channels, we employed a hybrid method of dictionary and corpus-based lexicon approaches to achieve the wordlist derivation. The result advocates for an alternative way of reporting negative news to reduce the adverse impact it has on the masses.

An Improved Lexicon Based Model for Efficient Sentiment Analysis on Movie Review Data

Every day a large set of data are collected for various purposes from different sources. Analyzing these large data sets is very essential as we do not need to use all the information depending on the application usage. Hence, mining this data set including text and sentiment is gradually becoming very important and useful for application purposes. Market analysis experts make plans for any production by taking into account the users’ feedback and buying habits. Using different sentiment analysis methods, these tasks can be accomplished successfully. In our research, we discuss here the existing lexicon analysis method and find out the limitations of its methodology, e.g., lower accuracy. Although some researchers have proposed and compared the accuracy of their models with the existing lexicon approaches, our proposed and developed customized model shows good accuracy for movie data reviews compared to the existing approaches.

L2b: Lexicon Boosted Bayesian Classification For Popularity Prediction Of Movies With Improved Accuracy Using Twitter Corpus

Social networking plays a vital role in the research phenomenon. It helps in acquiring the most recent news and information consistently with settling on ground-breaking choices and expectations. There are enormous expressions of people opinion in addition to what's circumventing the world. Twitter, is a well known blogging site where individuals place their perspectives and inclinations based on their interest. This paper presents a Lexicon Boosted Bayesian (L2B) classification for popularity prediction of movies based on twitter corpus. The proposed approach predicts the accomplishment of the film utilizing perspective individuals that might actually be accomplished by assessment examination with Naive Bayes classification and Lexicon approach. In addition, it focuses with the representation of information in R language which stands the best in speaking to the investigation in pictorial arrangement and a guide perception that depicts the area of the tweets where it has come from. The result analysis proves the effectiveness of proposed technique in comparison with the existing approaches for predicting the success of the movies.

The Walls Have Ears: Accessing Participant Narratives amid Silence, Secrecy, and Mistrust

Eritreans have long been considered a close-knit community bound by the memorialisation of history and the preservation of cultural practices. My anthropological enquiry into the everyday experiences of mental distress among diasporic women revealed that the depth of their exclusivity was a response to the continual and unsystematic surveillance of the Eritrean state. Government spies targeted outspoken critics, either forcing them into exile or pushing them into perpetual silence. In this essay, I explain how the perceived looming presence of secret agents created widespread mistrust and pervasive silence that complicated relationship-building among diasporic women. I then describe how negative perceptions of the term ‘mental health’ required an alteration of my lexicon and methodological approach, revealing the embodiments of silence and distress in everyday interactions. By reflexively and critically engaging with women’s everyday experiences, silence emerges as a central theme in my work, eventually becoming a conceptual anchor that has helped me understand and connect with a politically silenced diaspora. Through these ethnographic encounters, the complexities of the social, cultural, and political interactions gave meaning to simple utterances.

Social Media Sentiment Analysis: The Hajj Tweets Case Study

About forty five percent of the world's population use social networks, thinking of using these platforms seemed to find people's opinions and feelings on various topics. Companies that offer their services and products to customers focus on the subject for future improvement. Thus, serious thinking began to analyze the views of people across different social platforms and also to develop the best ways to analyze these views. In this study, we focused on finding the best way for sentiment analysis by using a series of Hajj-related tweets, which is one of the most important rituals performed by Muslims, where the companies responsible for the pilgrimage season seek to complete the season in best way every year. We used the Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naive Bayes (NB) as supervised algorithms for machine-learning approach and Text Blob analyzer for lexicon-based approach. Finding shows that, machine learning techniques worked better than the lexicon approach in the classification and analysis of Hajj related tweets. Even the limited availability of Hajj tweets corpus dataset, SVM reaches the best accuracy which was 84%.

Bilingual Lexicon Approach to English-Filipino Sentiment Analysis of Teaching Performance

The aim of this study is to formulate a strategy that can possibly calculate teacher performance by analyzing textual feedback. Expressing textual responses in quantitative form like average sentiment rating can actually provide opportunities for administrators to see if the numerical ratings given complement that of the comments. Our approach was designed to enable processing bilingual textual data. Findings of this study shows that there is strong correlation between teaching performance actual mean rating and average sentiment rating. Furthermore, the approach employed obtained 86% accuracy indicating that it is an encouraging technique, capable of analyzing the students' textual responses. In future work, the use of POS tagging can be explored to improve sentiment analysis accuracy. Employing machine learning methods may also be considered to discover techniques and alternative approaches to sentiment classification.

A Novel Approach for Sentiment Analysis Using Deep Recurrent Networks and Sequence Modeling

Background: Due to the increasing growth of social websites, a lot of user-generated data is available these days in the form of customer reviews, opinions, and comments. Objective: Sentiment analysis includes analyzing the user reviews and finding the overall opinions from the reviews in terms of positive, negative and neutral categories. Sentiment analysis techniques can be used to assign a piece of text a single value that represents opinion expressed in that text. Sentiment analysis using lexicon approaches is already studied. Methods: A new approach to sentiment analysis using deep neural networks techniques is proposed. Deep neural networks using Sequence to sequence model is studied in this paper. The main objective of this paper is to identify the sequence of relationships among the words in the reviews. Customer reviews are taken from Amazon and sentiment analysis is done using the word embedding method. Results: The results obtained by the proposed method are compared with the baseline algorithms such as Naïve, and logistic regression. Conclusion: Confusion Matrix along with receiver operating characteristics and area under the curve is analyzed. The accuracy of the proposed methodology is compared with other algorithms.

Sentiment analysis of the NIGERIAN nationwide lockdown due to COVID19 outbreak

Sentiment analysis is a classification technique that specializes in categorizing a body of texts into various emotions. This categorization had proven to be handy in classifying tweets into positive, negative, or neutral emotions. Nigerians had been on a nationwide lockdown due to COVID19 since 30th March 2020. The analysis of the emotions of Nigerians during this period is expedient to understand the effectiveness of exercise and the impact it has on the masses. The focus of this paper is to determine the sentiment analysis of Nigerians within the period of the lockdown exercise. Using a lexicon-based analytic architecture and a streaming API to TwitterNG, we extracted a total of 22, 249 tweets from the timelines of national stakeholders on COVID19 and location-based tweets from the general public. The tweets were extracted and collated using a set of ten hashtags/keywords from 30th March to 11th May 2020. The analysis was done in R Programming Software with the application of the NRC lexicon approach to classifying the emotions of Nigerians within the period. The result showed that Nigerians expressed an overall positive sentiment to the lockdown exercise despite a few negative expressions.

A Sentiment Analysis Model for Terrorist Attacks Reviews on Twitter

Twitter is considered as one of the famous microblogs that attract politicians and individuals to express their views on political, economic and social issues. The phenomenon of terrorist operations is one of the largest security and economic problem facing the world in recent years. Twitter users' comments on terrorism issues are important to understand users' sentiment about terrorist events. Sentiment analysis is a field of research for understanding and extracting users’ views. In this paper, we propose a model for automatically classifying users’ reviews on Twitter after occurrence of a terrorist attack, the model is built using lexicon and machine learning approaches. Lexicon approach is used to create labelled training dataset while machine learning approach was used to build the model. Scores of some domain related words were neutralized to avoid their negative effect. Features were selected based on PoS. Majority voting between NB, SVM and LR machine learning classification algorithms was applied. The performance of classification algorithms was measured using accuracy and F1 scores. The results obtained are compared to identify the best classification algorithm for features selection. Result show that our model achieved 94.8% accuracy with 95.9% F1 score.

Word Analysis of Indonesian Keirsey Temperament

Personality uniquely relates to our feeling and pattern to the aspect of actions. This behavior will change through the experience, formal education, and the surrounding environment. This works based on the Keirsey Temperament Sorter, a personality questionnaire developed by David Keirsey. This model divides the personality into four categories as Idealists, Rationals, Guardians, and Artisans. This concept is commonly recognized for the interpretation of specialist trends, potentially contributes to the process of recruitment or selection, and potential fields for analysis of social media data. Words selected by using Chi-Square with an error of 5%. Accuracy of the lexicon approach is 34%, while the best machine learning approach is Random Forest algorithm with 69.59%

Shaping up the Future Spatial Plans for Urban Areas in Pakistan

Since 2007, more than fifty percent of our planet’s population is living in urban areas. In the coming decade, the rate of urbanization will be fastest in Asia and Africa. Within South Asian countries, urbanization has attained its fastest pace in Pakistan. Urban planners and agencies in Pakistan have tried various spatial plan making solutions to manage urban areas, but none have given the desired results. After a 20% increase in declared urban areas within last two decades, urban planners and policy makers are looking for a more innovative and realistic spatial planning solution, which could adjust to the uncertainties and complexities of real world. This research uses a mixed method approach comprising a two phased survey of professional planners, analyzed through the selective lexicon approach to document planners’ opinions about the reasons behind the poor performance and conformance of spatial plans. This study documents the planners’ understanding of the contemporary concept of ‘scenario planning’. To explore the solution, this paper presents a semi-systematic review of the literature on the application of the ‘scenario method in urban spatial planning’. As a result of this research, a comprehensive digital inventory of all spatial plans ever made in Pakistan has been developed. It has been found that 83% of the urban settlements in Pakistan are growing without a spatial plan and require immediate attention. Furthermore, in terms of the plan making process, twenty-seven major factors contributing to the failure of past plans have been identified and categorized under seven distinct plan making stages. Finally, a new process of spatial plan-making has been proposed, which is the fusion of scenario planning and the traditional plan-making process, backed by digital planning tools. In an era of smart cities and digitization, it is expected that the advancements in scenarios planning, coupled with a new data portal, will assist in addressing the implementation gap in practice, and result in more comprehensive data-driven spatial plans.

Towards Integrated Classification Lexicon for Handling Unknown Words in Chinese-Vietnamese Neural Machine Translation

In Neural Machine Translation (NMT), due to the limitations of the vocabulary, unknown words cannot be translated properly, which brings suboptimal performance of the translation system. For resource-scarce NMT that have small-scale training corpus, the effect is amplified. The traditional approach of amplifying the scale of the corpus is not applicable, because the parallel corpus is difficult to obtain in a resource-scarce setting; however, it is easy to obtain and utilize external knowledge, bilingual lexicon, and other resources. Therefore, we propose classification lexicon approach for processing unknown words in the Chinese-Vietnamese NMT task. Specifically, three types of unknown Chinese-Vietnamese words are classified and their corresponding classification lexicon are constructed by word alignment, Wikipedia extraction, and rule-based methods, respectively. After translation, the unknown words are restored by lexicon for post-processing. Experiment results on Chinese-Vietnamese, English-Vietnamese, and Mongolian-Chinese translations show that our approach significantly improves the accuracy and the performance of NMT especially in a resource-scarce setting.

Enhanced Techniques for Opinion Mining

The exponential growth of online information sharing has led to the need to analyze them. Opinion Mining or Sentiment Analysis incorporates a systematic approach to favor analysis of the available online synthesized data .This paper includes a lexicon based approach towards analysis. The proposed SLN (Slang Negation) Algorithm follows a lexicon based approach to Opinion Mining. The slang lexicon provides the expansion of the acronyms and their scores. Three types of negations namely explicit, implicit and pseudo negation are handed. Slang and negation handling are necessary to support semantic orientation. The proposed SLN algorithm has shown significant improvement in the precision, recall, f-measure and accuracy values as compared to the use of sentiment lexicon approach.

Identification of Abusive Sinhala Comments in Social Media using Text Mining and Machine Learning Techniques

With the technology revolution, most of the natural languages that are used all over the world have won the digital world. Therefore, people use modern technologies such as Social Media and the Internet with their native languages. As a result, people who are with self-ego on their tradition, race, caste, religion and other social factors, tend to make abusiveness on others who do not belong to the same social group by their native languages. Since the Social Media platforms do not have centralized control, it has become a good platform to advertise their backward ideas without being governed and monitored. The Sinhala language has also been added to most famous Social Media platforms. Though the Sinhala language has more than 2500 years of history, it does not have rich resources for computer-based natural language processing. Therefore, it has been a very difficult task to automatically detect Sinhala abusive comments which are being published and shared among Social Media platforms. Therefore, here, we have used evenly distributed 2000 Sinhala comment corpus among offensive and neutral classes to train three different models: Multinomial Naïve Bayes (MNB), Support Vector Machine (SVM) and, Random Forest Decision Tree (RFDT) and the features were extracted from Bag of Word model, word n-gram model, character n-gram model, and word skip-gram model to automatically detect Sinhala abusive comments. After the training process, each model was tested with 200 evenly distributed comment corpus and MNB showed the highest accuracy of 96.5% with 96% average recall for both character tri-gram and character four-gram models. Further, two lexicon-based approaches called cross-lingual lexicon approach and corpus-based lexicon approach were considered to detect Sinhala abusive comments. From these two lexicon based approaches, the corpus-based lexicon gave the highest accuracy of 90.5% with an average recall of 90.5%.

Understanding Destination Image in UGC: A Lexicon Approach

Understanding Destination Image in UGC: A Lexicon Approach

Sentiment Analysis of the Nigerian Nationwide Lockdown Due to COVID19 Outbreak

Sentiment analysis is a classification technique that specializes in categorizing a body of texts into various emotions. This categorization had proven to be handy in classifying tweets into positive, negative, or neutral emotions. Nigerians had been on a nationwide lockdown due to COVID19 since 30th March 2020. The analysis of the emotions of Nigerians during this period is expedient to understand the effectiveness of exercise and the impact it has on the masses. The focus of this paper is to determine the sentiment analysis of Nigerians within the period of the lockdown exercise. Using a lexicon-based analytic architecture and a streaming API to TwitterNG, we extracted a total of 22, 249 tweets from the timelines of national stakeholders on COVID19 and location-based tweets from the general public. The tweets were extracted and collated using a set of ten hashtags/keywords from 30th March to 11th May 2020. The analysis was done in R Programming Software with the application of the NRC lexicon approach to classifying the emotions of Nigerians within the period. The result showed that Nigerians expressed an overall positive sentiment to the lockdown exercise despite a few negative expressions.