Suchergebnisse

Sentiment analysis (SA) is one of the fastest growing research areas in Natural Language Processing, making it challenging to keep track of all the activities in the area. Increase in user-generated content (UGC) has provided an important aspect for the researchers, industries and government(s) to mine this information. SA mine information from UGC on the basis of polarity as positive, negative or neutral. The problem domain, to which this research is concerned, is to find the sentiment and its respective aspect in the sentence and finally to calculate the overall sentiment score of entered Hindi text to classify each sentence as positive, negative and neutral. In this thesis, we work on the sentiment analysis by devolving an algorithm that identifying the sentiment according to proposed rules based on positions of conjunction, negation and aspects (nouns).

International Journal of Advanced Computer Science and Applications(IJACSA), 9(10), 2018 ; Sentiment Analysis is problem of natural language processing which deals with the extraction and analysis of public sentiments shared about target entities over microbloging websites. This field has gained great attention due to the huge availability of decision making textual contents. Sentiment Analysis has enormous application areas such as; Market Analysis, Service Analysis, Showbiz analysis, Movies, sports and even the popularity and acceptance rate of political policies can also be predicted via sentiment analysis systems. Although tremendous volume of opinionative text is available but it is unstructured and noisy due to which sentiment classifiers can't achieve good outcomes. Normalization is the process used to clean noise from unstructured text for sentiment analysis. In this study we have proposed a mechanism for the normalization of informal and unstructured text. Proposed mechanism is comprised of four essential phases; Noise Reduction, Part of Speech Tagging, Stop Word Removal stemming and Lemmatization. Numerous experiments are performed on twitter data set with unsupervised lexicons and dictionaries. Python and Natural language toolkit is used for performing all four essential steps. This study demonstrates that utilization and normalization of informal tokens in tweets improved the overall classification accuracy from 75.42 to 82.357. ; http://thesai.org/Downloads/Volume9No10/Paper_11-Normalization_of_Unstructured_and_Informal_Text.pdf

Sarcasm is one of the problem that affect the result of sentiment analysis. According to Maynard and Greenwood (2014), performance of sentiment analysis can be improved when sarcasm also identified. Some research used Naïve Bayes and Random Forest method on sentiment analysis process. On Salles, dkk (2018) research, in some cases Random Forest outperform the performance by Support Vector Machine that known as a superior method. In this research, we did sentiment analysis on comment section on Instagram account of Indonesian politician. This research compare the accuracy of sentiment analysis with sarcasm detection and analysis sentiment without sarcasm detection, sentiment analysis with Naïve Bayes and Random Forest method then Random Forest for sarcasm detection. This research resulted in accuracy value in sentiment analysis without sarcasm detection with Naïve Bayes 61%, with Random Forest method 72%. Accuracy on sentiment analysis with sarcasm detection using Naïve Bayes – Random Forest method is 60% and using Random Forest – Random Forest method is 71%.

Abstract Twitter is a microblog-based social media site launched on July 13, 2006. In March 2020, 476.696 tweets about the government policy in COVID-19 spread on Twitter were captured by the Institute for Development of Economics and Finance (Indef). Government policy has a standard meaning, namely a decision systematically made by the government with specific goals and objectives relating to the public interest, whether carried out directly or indirectly. Sentiment analysis analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. In this decade, Sentiment Analysis is has become a trendy research area. The purpose of this paper is to focus how to implement word2vec using similarity word as a feature expansion for minimize the vocabulary mismatch in Twitter Sentiment Analysis using "word embeddings". This research contains 11.395 tweets for a dataset, where the dataset will be used in two classifications: Support Vector Machine Algorithm and Artificial Neural Network Algorithm. The output of Word2Vec will be used for feature expansion in this research, where the algorithm of expansion will check in each row in the corpus where has a similarity vector with that word and will replace the word with the similarity of this words if the value is 0. The dataset in Feature Expansion is using 142.545 articles from Indonesian media. The result of this research is ANN is better than SVM, where the ANN without feature expansion gets 68.89 % and using feature expansion gets 72.58 %. For SVM, the final accuracy without feature expansion is 63.95 %, and using feature expansion gets 68.56 %. This research proves that feature expansion can improve the final accuracy. ; Abstract Twitter is a microblog-based social media site launched on July 13, 2006. In March 2020, 476.696 tweets about the government policy in COVID-19 spread on Twitter were captured by the Institute for Development of Economics and Finance (Indef). Government policy has a standard meaning, namely a decision systematically made by the government with specific goals and objectives relating to the public interest, whether carried out directly or indirectly. Sentiment analysis analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. In this decade, Sentiment Analysis is has become a trendy research area. The purpose of this paper is to focus how to implement word2vec using similarity word as a feature expansion for minimize the vocabulary mismatch in Twitter Sentiment Analysis using "word embeddings". This research contains 11.395 tweets for a dataset, where the dataset will be used in two classifications: Support Vector Machine Algorithm and Artificial Neural Network Algorithm. The output of Word2Vec will be used for feature expansion in this research, where the algorithm of expansion will check in each row in the corpus where has a similarity vector with that word and will replace the word with the similarity of this words if the value is 0. The dataset in Feature Expansion is using 142.545 articles from Indonesian media. The result of this research is ANN is better than SVM, where the ANN without feature expansion gets 68.89 % and using feature expansion gets 72.58 %. For SVM, the final accuracy without feature expansion is 63.95 %, and using feature expansion gets 68.56 %. This research proves that feature expansion can improve the final accuracy.

Traditionally, the evaluation of political biases in Danish newspapers has been carried out throughhighly subjective methods. The conventional approach has been surveys asking samples of thepopulation to place various newspapers on the political spectrum, coupled with analysing votinghabits of the newspapers' readers (Hjarvard, 2007). This paper seeks to examine whether it ispossible to use sentiment analysis to objectively assess political biases in Danish newspapers. Byusing the sentiment dictionary AFINN (Nielsen et al., 2011), the mean sentiment scores for 360articles was calculated. The articles were published in the Danish newspapers Berlingske andInformation and were all regarding the political parties Alternativet and Liberal Alliance. Asignificant interaction effect between the parties and newspapers was discovered. This effect wasmainly driven by Information's coverage of the two parties. Moreover, Berlingske was found topublish a disproportionately greater number of articles concerning Liberal Alliance thanAlternativet. Based on these findings, an integration of sentiment analysis into the evaluation ofbiases in news outlets is proposed. Furthermore, future studies are suggested to construct datasetsfor evaluation of AFINN on news and to utilize web-mining methods to gather greater amounts ofdata in order to analyse more parties and newspapers.

There are various techniques used by the investors for the prediction of future price of a stock or the trend of the entire stock market. Fewparameters on which the movement of the stock depends are the performance of the company, political events such as the suddenfluctuation in the rise or fall of the currency, etc. This paper majorly focuses on the sentiments of the investors which depend on fewparameters such as any scam news, current condition of the whole economy, peer organization execution, and so forth. In view of theseboundaries, the supposition of a financial specialist might be positive, negative or unbiased. Here, we will perceive how the estimations ofa speculator affect the cost of the stock so we can anticipate the right cost of the stock. Suppositions assume a significant job in the financialexchange and we can come to realize how financial exchange responds to various sort of information climate real or phony. Consequently,a methodology of assumption examination for securities exchange expectation has been arisen to foresee the effect on financial exchangedependent on human opinions.

We revisit the discussion of market sentiment in European sovereign bonds using a correlation analysis toolkit based on influence networks and hierarchical clustering. We focus on three case studies of political interest. In the case of the 2016 Brexit referendum, the market showed negative correlations between core and periphery only in the week before the referendum. Before the French presidential elections in 2017, the French bond spread widened together with the estimated Le Pen election probability, but the position of French bonds in the correlation blocks did not weaken. In summer 2018, during the budget negotiations within the new Italian coalition, the Italian bonds reacted very sensitively to changing political messages but did not show contagion risk to Spain or Portugal for several months. The situation changed during the week from October 22 to 26, as a spillover pattern of negative sentiment also to the other peripheral countries emerged.

Now a day Social Media like Facebook, twitter and Instagram is major Sources for people to share their emotions based on the current situations in society. By knowing the interesting patterns in it, a government/appropriate person for that situation can take good and useful decisions. Sentiment analysis is a method where people can extract the useful information from the text like the emotions (happy, sad, and neutral) of people. Much research work was been underdoing in the area of sentiment analysis. Among that work the Machine learning and Deep learning approaches plays a maximum role. Existing works on sentiment analysis is going in the English language. In this paper, proposed a novel framework that specifically designed to do sentiment analysis of the text data, that available in the telugu language. The proposed framework was integrated with the word embedding model Word2Vec, language translator and deep learning approaches like Recurrent Neural Network and Navie base algorithms to collect and analyse the sentiment in tweeter data that present in telugu language. The results shows effective in terms of accuracy, precision and specificity.

People's opinions are considered as the most powerful source of market research. Popularly, Social Media has become a tool that is used in an easy way including huge number of users who can share their opinions about products or services and their thoughts about current problems of the society and express their views on political and religious issues. The knowledge extracted from social media contains sentiment data – that is not included in corporate database – that can be used to improve the marketing campaigns to retain customers and meet their needs in a better way. The integration and merging between both social media data and corporate data can lead to better insights that would not have been possible to gain without such integration. In this paper, we will use Twitter as a social media source platform to do a feature based level sentiment analysis using tweets including opinions about a specific product. . The research discussed three different ways to extract (feature/opinion) pairs from each text including: Normal Tokenization, N-gram Modeling Extraction, and Noun Chunking Extraction. The extracted opinion phrase related to each extracted feature is being classified using sentiment classification algorithm. A decision is taken about the best between the three ways according to the resulted measurements. SCDJF had been evaluated using multiple techniques. The best results occurred from Noun Chunking Extraction with accuracy 77%. Summarization of the results will show how this can be used to enhance decision making process of the organization. Summarization of the results will show how this can be used to enhance decision making process of the organization.

Negation is a linguistic phenomenon that can cause sentences to have their meanings reversed. It frequently inverts affirmative sentences into negative ones, affecting the polarity; therefore, the sentiment of the text also changes accordingly. Negation can be expressed differently, making it somewhat challenging to detect. As a result, detecting negation is critical for Sentiment Analysis (SA) system development and improvement and will increase classifier accuracy, but it also poses a significant conceptual and technical challenge. This paper aims to survey and gather the most recent research related to detecting negation in SA. Many researchers have worked and performed methods, including algorithmic, machine, and deep learning approaches such as Decision Tree (DT), Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Naive Bayesian (NB), Logistic Regression (LR), Artificial Neural Networks (ANNs), Recurrent Neural Networks (RNNs), Bidirectional Long Short-Term Memory (BiLSTM), and other hybrid methods such as rule-based and machine learning, lexicon and machine learning, machine learning, and deep learning. It addresses and tries to identify the gaps in the current studies, laying the foundation for future studies in this field.

This article presents a new methodology to quantify the probability and magnitude of combinations of emotions -called dyads- through a sentiment analysis which provides prior probabilities of the basic emotions, needed to show the presence of dyads in profiles of people. We classify these features -probability and magnitude- of the dyads into six groups (max, highest, high, medium, low, lowest) in order to identify dyads that have more impact in what we call in this work: positive, negative, neutral, and combined profiles. Positive profiles present mainly Love, while negative profiles present Contempt and Regret. In general, the magnitude of the primary dyads is greater than their probability, not so with the secondary and tertiary dyads where their probability is greater than their magnitude.

With the rapid growth of internet technology since early 19th century, there was a tremendous change in the global communication from all over the world. Technology advancements in world wide web has lead a great influence on people communication, as people started communicating in social websites, forums, blogs to express their behavior on particular issue, which showed direct or indirect affect on marketing strategies of an organization, political issues, movie reviews etc., Thus research in this area progressed very rapidly from early mid 90`s . Several techniques, methodologies have been addressed to study the sentiment of people behavior over the internet. The popularity of research in opinion mining and sentiment analysis involved the study of several natural language processing (NLP) techniques. Thus opinion mining is a concept of implementing NLP techniques on the user input given to computer via internet sources. Whereas, Sentiment analysis is used to extract emotions, to extract subject on the issue, and to find out impact on user quoted mined opinions. As NLP techniques used in opinion mining and sentiment analysis addresses many issues like parts of speech tagging-POS, negation rules, word sentiment classification. Hence this paper addresses the following aspects, important for mining opinions and classifying them using semi-supervised naive bayes classifier.

In the age of social media, everyone has the ability to post their thoughts and feelings about several topics on the Internet for the world to see. Major social media platforms such as Facebook, Twitter, and Instagram are used to connect users across the globe to share photos and discuss trending topics. Trending topics can include sociopolitical issues or restaurant, movie and product reviews. Given the vast amount of data accumulated through the use of these platforms, sentiment analysis is a natural language process technique that can be used to assess public opinion of said topics. Sentiment analysis also has application potential in marketing and politics. Businesses can use it to discover public opinion of their products in real-time and understand how to better market their products to target consumers. Political analysts can use sentiment analysis to discover the likability of candidates for office amongst voters, which could aid in predicting the probability of winning elections. In this paper, Twitter data was used to conduct sentiment analysis to gauge public opinion regarding Android and iPhone devices. Additionally, data visualization techniques were used to help tell the story of the data and present it in a pictorial view. Anaconda and Jupyter environments were used to develop and execute Python code to query against Twitter's API, retrieve relevant tweets regarding iPhone and Android devices, transform and manipulate the data, and provide several graphical depictions of the result set. A system architecture diagram was presented to display the inner workings and flow process of the experiment. Lastly, the experiment conducted a comparison between Twitter's sentiment polarity classifier and the ANEW dictionary to determine which device was favored amongst users.

Traditionally, the evaluation of political biases in Danish newspapers has been carried out through highly subjective methods. The conventional approach has been surveys asking samples of the population to place various newspapers on the political spectrum, coupled with analysing voting habits of the newspapers' readers (Hjarvard, 2007). This paper seeks to examine whether it is possible to use sentiment analysis to objectively assess political biases in Danish newspapers. By using the sentiment dictionary AFINN (Nielsen et al., 2011), the mean sentiment scores for 360 articles was calculated. The articles were published in the Danish newspapers Berlingske and Information and were all regarding the political parties Alternativet and Liberal Alliance. A significant interaction effect between the parties and newspapers was discovered. This effect was mainly driven by Information's coverage of the two parties. Moreover, Berlingske was found to publish a disproportionately greater number of articles concerning Liberal Alliance than Alternativet. Based on these findings, an integration of sentiment analysis into the evaluation of biases in news outlets is proposed. Furthermore, future studies are suggested to construct datasets for evaluation of AFINN on news and to utilize web-mining methods to gather greater amounts of data in order to analyse more parties and newspapers.

entiment classification has become a ubiquitous enabling technology in the Twittersphere, since classifying tweets according to the sentiment they convey towards a given entity (be it a product, a person, a political party, or a policy) has many applications in political science, social science, market research, and many others. In this paper, we contend that most previous studies dealing with tweet sentiment classification (TSC) use a suboptimal approach. The reason is that the final goal of most such studies is not estimating the class label (e.g., Positive, Negative, or Neutral) of individual tweets, but estimating the relative frequency (a.k.a. "prevalence") of the different classes in the dataset. The latter task is called quantification, and recent research has convincingly shown that it should be tackled as a task of its own, using learning algorithms and evaluation measures different from those used for classification. In this paper, we show (by carrying out experiments using two learners, seven quantification-specific algorithms, and 11 TSC datasets) that using quantification-specific algorithms produces substantially better class frequency estimates than a state-of-the-art classification-oriented algorithm routinely used in TSC. We thus argue that researchers interested in tweet sentiment prevalence should switch to quantification-specific (instead of classification-specific) learning algorithms and evaluation measures. This is an extended version of a paper with the title "Tweet Sentiment: From Classification to Quantification" which appears in the Proceedings of the 6th ACM/IEEE International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2015).