Conference Paper

Towards a Performant Multilingual Model Based On Ensemble Learning to Enhance Sentiment Analysis

If you want to read the PDF, try requesting it from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
Aspect Based Sentiment Analysis (ABSA) aims at collecting detailed opinion information according to products and their features, via the recognition of targets of the opinions in text. Though some annotated data have been produced in challenges as SemEval, resources are still scarce, especially for languages other than English. We are interested in enhancing today's mostly statistical text classification with the use of linguistics tools, in order to better define and analyze what has been written. The work presented in this paper focuses on two French datasets of movies and books online reviews. In reviews, text length is much higher compared to a tweet, giving us the opportunity to work on a challenging and linguistically interesting dataset. Moreover, movies and books are products that make classifying opinions into aspects quite complex. This article provides an analysis of the particularities of the two domains during the process of collecting and annotating data, a precise annotation scheme for each domain, examples and statistics issued from the annotation phase, and some perspectives on our future work.
Conference Paper
Full-text available
Aspect based sentiment analysis aims to detect an aspect (i.e. features) in a given text and then perform sentiment analysis of the text with respect to that aspect. This paper aims to give a solution for the FiQA 2018 challenge subtask 1. We perform aspect-based sentiment analysis on the microblogs and headlines of financial domain. We use a multi-channel convolutional neural network for sentiment analysis and a recurrent neural network with bidirectional long short-term memory units to extract aspect from a given headline or microblog. Our proposed model produces a weighted average F1 score of 0.69 for the aspect extraction task and predicts sentiment intensity scores with a mean squared error of 0.112 on 10-fold cross validation. We believe that the developed system has direct applications in the financial domain.
Article
Full-text available
Research on sentiment analysis in English language has undergone major developments in recent years. Chinese sentiment analysis research, however, has not evolved significantly despite the exponential growth of Chinese e-business and e-markets. This review paper aims to study past, present, and future of Chinese sentiment analysis from both monolingual and multilingual perspectives. The constructions of sentiment corpora and lexica are first introduced and summarized. Following, a survey of monolingual sentiment classification in Chinese via three different classification frameworks is conducted. Finally, sentiment classification based on the multilingual approach is introduced. After an overview of the literature, we propose that a more human-like (cognitive) representation of Chinese concepts and their inter-connections could overcome the scarceness of available resources and, hence, improve the state of the art. With the increasing expansion of Chinese language on the Web, sentiment analysis in Chinese is becoming an increasingly important research field. Concept-level sentiment analysis, in particular, is an exciting yet challenging direction for such research field which holds great promise for the future.
Conference Paper
Full-text available
This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual approaches typically require to establish a correspondence to English for which powerful classifiers are already available. In contrast, our method does not require such supervision. We leverage large amounts of weakly-supervised data in various languages to train a multi-layer convolutional network and demonstrate the importance of using pre-training of such networks. We thoroughly evaluate our approach on various multi-lingual datasets, including the recent SemEval-2016 sentiment prediction benchmark (Task 4), where we achieved state-of-the-art performance. We also compare the performance of our model trained individually for each language to a variant trained for all languages at once. We show that the latter model reaches slightly worse - but still acceptable - performance when compared to the single language model, while benefiting from better generalization properties across languages.
Conference Paper
Full-text available
English. In this paper, we propose a clas-sifier for predicting sentiments of Italian Twitter messages. This work builds upon a deep learning approach where we leverage large amounts of weakly labelled data to train a 2-layer convolutional neural network. To train our network we apply a form of multi-task training. Our system participated in the EvalItalia-2016 competition and outperformed all other approaches on the sentiment analysis task. In questo articolo, presentiamo un sis-tema per la classificazione di soggettività e polarità di tweet in lingua italiana. L'approccio descritto si basa su reti neu-rali. In particolare, utilizziamo un dataset di 300M di tweet per addestrare una con-volutional neural network. Il sistemà e stato addestrato e valutato sui dati for-niti dagli organizzatori di Sentipolc, task di sentiment analysis su Twitter organiz-zato nell'ambito di Evalita 2016..
Article
Full-text available
This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual approaches typically require to establish a correspondence to English for which powerful classifiers are already available. In contrast, our method does not require such supervision. We leverage large amounts of weakly-supervised data in various languages to train a multi-layer convolutional network and demonstrate the importance of using pre-training of such networks. We thoroughly evaluate our approach on various multi-lingual datasets, including the recent SemEval-2016 sentiment prediction benchmark (Task 4), where we achieved state-of-the-art performance. We also compare the performance of our model trained individually for each language to a variant trained for all languages at once. We show that the latter model reaches slightly worse - but still acceptable - performance when compared to the single language model, while benefiting from better generalization properties across languages.
Conference Paper
Full-text available
Sentiment analysis has become a key tool for several social media applications, including analysis of user's opinions about products and services, support to politics during campaigns and even for market trending. There are multiple existing sentiment analysis methods that explore different techniques, usually relying on lexical resources or learning approaches. Despite the large interest on this theme and amount of research efforts in the field, almost all existing methods are designed to work with only English content. Most existing strategies in specific languages consist of adapting existing lexical resources, without presenting proper validations and basic baseline comparisons. In this paper, we take a different step into this field. We focus on evaluating existing efforts proposed to do language specific sentiment analysis. To do it, we evaluated twenty-one methods for sentence-level sentiment analysis proposed for English, comparing them with two language-specific methods. Based on nine language-specific datasets, we provide an extensive quantitative analysis of existing multi-language approaches. Our main result suggests that simply translating the input text on a specific language to English and then using one of the existing English methods can be better than the existing language specific efforts evaluated. We also rank those implementations comparing their prediction performance and identifying the methods that acquired the best results using machine translation across different languages. As a final contribution to the research community, we release our codes and datasets. We hope our effort can help sentiment analysis to become English independent.
Article
Full-text available
So far different studies have tackled the sentiment analysis in several domains such as restaurant and movie reviews. But, this problem has not been studied in scholarly book reviews which is different in terms of review style and size. In this paper, we propose to combine different features in order to be presented to a supervised classifiers which extract the opinion target expressions and detect their polarities in scholarly book reviews. We construct a labeled corpus for training and evaluating our methods in French book reviews. We also evaluate them on English restaurant reviews in order to measure their robustness across the domains and languages. The evaluation shows that our methods are enough robust for English restaurant reviews and French book reviews.
Conference Paper
Full-text available
There is a remarkable growth in the usage of social networks, such as Facebook and Twitter. Users from different cultures and backgrounds post large volumes of textual comments reflecting their opinion in different aspect of life and make them available to everyone. In particular we study the case of Twitter and focus on presidential elections in Egypt 2012. This paper compares between two techniques for Arabic text classification using WEKA application. These techniques are Support Vector Machine (SVM) and Naïve Bayesian (NB), we investigate the use of TF-IDF to obtain document vector. The main objective of this paper is to measure the accuracy and time to get the result for each classifier and to determine which classifier is more accurate for Arabic text classification. Comparison reported in this paper shows that the Naïve Bayesian method is the highest accuracy and the lowest error rate.
Article
Full-text available
Due to the vast amount of user-generated content in the emerging Web 2.0, there is a growing need for computational processing of sentiment analysis in documents. Most of the current research in this field is devoted to product reviews from websites. Microblogs and social networks pose even a greater challenge to sentiment classification. However, especially marketing and political campaigns leverage from opinions expressed on Twitter or other social communication platforms. The objects of interest in this paper are the presidential candidates of the Republican Party in the USA and their campaign topics. In this paper we introduce the combination of the noun phrases' frequency and their PMI measure as constraint on aspect extraction. This compensates for sparse phrases receiving a higher score than those composed of high-frequency words. Evaluation shows that the meronymy relationship between politicians and their topics holds and improves accuracy of aspect extraction.
Conference Paper
Full-text available
Due to the fact that majority of web content is provided within collaborative environments such as social media and social networks systems its complexity brings a new strong need for its accurate aggregation and understanding. Sentiment analysis (also known as opinion mining) is one of possibility to understand generated content that may brings an interesting summation in terms of attitudes expressed in texts. The paper proposes a new approach to sentiment analysis of polish language using machine learning approach.
Article
Full-text available
The fact that people freely express their opinions and ideas in no more than 140 characters makes Twitter one of the most prevalent social networking websites in the world. Being popular in Saudi Arabia, we believe that tweets are a good source to capture the public’s sentiment, especially since the country is in a fractious region. Going over the challenges and the difficulties that the Arabic tweets present – using Saudi Arabia as a basis – we propose our solution. A typical problem is the practice of tweeting in dialectical Arabic. Based on our observation we recommend a hybrid approach that combines semantic orientation and machine learning techniques. Through this approach, the lexical-based classifier will label the training data, a time-consuming task often prepared manually. The output of the lexical classifier will be used as training data for the SVM machine learning classifier. The experiments show that our hybrid approach improved the F-measure of the lexical classifier by 5.76% while the accuracy jumped by 16.41%, achieving an overall F-measure and accuracy of 84 and 84.01% respectively.
Article
Full-text available
The growing incidents of counterfeiting and associated economic and health consequences necessitate the development of active surveillance systems capable of producing timely and reliable information for all stake holders in the anti-counterfeiting fight. User generated content from social media platforms can provide early clues about product allergies, adverse events and product counterfeiting. This paper reports a work in progresswith contributions including: the development of a framework for gathering and analyzing the views and experiences of users of drug and cosmetic products using machine learning, text mining and sentiment analysis, the application of the proposed framework on Facebook comments and data from Twitter for brand analysis, and the description of how to develop a product safety lexicon and training data for modeling a machine learning classifier for drug and cosmetic product sentiment prediction. The initial brand and product comparison results signify the usefulness of text mining and sentiment analysis on social media data while the use of machine learning classifier for predicting the sentiment orientation provides a useful tool for users, product manufacturers, regulatory and enforcement agencies to monitor brand or product sentiment trends in order to act in the event of sudden or significant rise in negative sentiment.
Conference Paper
Full-text available
We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification. AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them. It consists of more than one composition functions, and we model the adaptive sentiment propagations as distributions over these composition functions. The experimental studies illustrate that AdaRNN improves the baseline methods. Furthermore, we introduce a manually annotated dataset for target-dependent Twitter sentiment analysis.
Article
Full-text available
We describe a state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the sentiment of a word or a phrase within a message (term-level task). The system is based on a supervised statistical text classification approach leveraging a variety of surface-form, semantic, and sentiment features. The sentiment features are primarily derived from novel high-coverage tweet-specific sentiment lexicons. These lexicons are automatically generated from tweets with sentiment-word hashtags and from tweets with emoticons. To adequately capture the sentiment of words in negated contexts, a separate sentiment lexicon is generated for negated words. The system ranked first in the SemEval-2013 shared task 'Sentiment Analysis in Twitter' (Task 2), obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. Post-competition improvements boost the performance to an F-score of 70.45 (message-level task) and 89.50 (term-level task). The system also obtains state-of-the-art performance on two additional datasets: the SemEval-2013 SMS test set and a corpus of movie review excerpts. The ablation experiments demonstrate that the use of the automatically generated lexicons results in performance gains of up to 6.5 absolute percentage points.
Article
Full-text available
We examine sentiment analysis on Twitter data. The contributions of this paper are: (1) We introduce POS-specific prior polarity fea- tures. (2) We explore the use of a tree kernel to obviate the need for tedious feature engineer- ing. The new features (in conjunction with previously proposed features) and the tree ker- nel perform approximately at the same level, both outperforming the state-of-the-art base- line. kernel based model. For the feature based model we use some of the features proposed in past liter- ature and propose new features. For the tree ker- nel based model we design a new tree representa- tion for tweets. We use a unigram model, previously shown to work well for sentiment analysis for Twit- ter data, as our baseline. Our experiments show that a unigram model is indeed a hard baseline achieving over 20% over the chance baseline for both classifi- cation tasks. Our feature based model that uses only 100 features achieves similar accuracy as the uni- gram model that uses over 10,000 features. Our tree kernel based model outperforms both these models by a significant margin. We also experiment with a combination of models: combining unigrams with our features and combining our features with the tree kernel. Both these combinations outperform the un- igram baseline by over 4% for both classification tasks. In this paper, we present extensive feature analysis of the 100 features we propose. Our ex- periments show that features that have to do with Twitter-specific features (emoticons, hashtags etc.) add value to the classifier but only marginally. Fea- tures that combine prior polarity of words with their parts-of-speech tags are most important for both the classification tasks. Thus, we see that standard nat- ural language processing tools are useful even in a genre which is quite different from the genre on which they were trained (newswire). Furthermore, we also show that the tree kernel model performs roughly as well as the best feature based models, even though it does not require detailed feature en-
Article
Full-text available
We describe the Open University team's submission to the 2011 i2b2/VA/Cincinnati Medical Natural Language Processing Challenge, Track 2 Shared Task for sentiment analysis in suicide notes. This Shared Task focused on the development of automatic systems that identify, at the sentence level, affective text of 15 specific emotions from suicide notes. We propose a hybrid model that incorporates a number of natural language processing techniques, including lexicon-based keyword spotting, CRF-based emotion cue identification, and machine learning-based emotion classification. The results generated by different techniques are integrated using different vote-based merging strategies. The automated system performed well against the manually-annotated gold standard, and achieved encouraging results with a micro-averaged F-measure score of 61.39% in textual emotion recognition, which was ranked 1st place out of 24 participant teams in this challenge. The results demonstrate that effective emotion recognition by an automated system is possible when a large annotated corpus is available.
Article
Full-text available
We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.
Article
Full-text available
The web contains a wealth of product reviews, but sifting through them is a daunting task. Ideally, an opinion mining tool would process a set of search results for a given item, generating a list of product attributes (quality, features, etc.) and aggregating opinions about each of them (poor, mixed, good). We begin by identifying the unique properties of this problem and develop a method for automatically distinguishing between positive and negative reviews. Our classifier draws on information retrieval techniques for feature extraction and scoring, and the results for various metrics and heuristics vary depending on the testing situation. The best methods work as well as or better than traditional machine learning. When operating on individual sentences collected from web searches, performance is limited due to noise and ambiguity. But in the context of a complete web-based tool and aided by a simple method for grouping sentences into attributes, the results are qualitatively quite useful.
Book
An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object. Opinion Mining and Sentiment Analysis covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. The focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. The survey includes an enumeration of the various applications, a look at general challenges and discusses categorization, extraction and summarization. Finally, it moves beyond just the technical issues, devoting significant attention to the broader implications that the development of opinion-oriented information-access services have: questions of privacy, vulnerability to manipulation, and whether or not reviews can have measurable economic impact. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided. Opinion Mining and Sentiment Analysis is the first such comprehensive survey of this vibrant and important research area and will be of interest to anyone with an interest in opinion-oriented information-seeking systems.
Conference Paper
This paper presents DyCorC, an extractor and cleaner of web forums contents. Its main points are that the process is entirely automatic, language-independent and adaptable to all kinds of forum architectures. The corpus is built accordingly to user queries using expressions or item keywords as in research engines, and then DyCorC minimizes the boilerplate for further feature-based opinion mining and sentiment analysis, gathering comments and scorings. Such noiseless corpora are usually hand made with the help of crawlers and scrapers, with specific containers devised for each type of forum, entailing lots of work and skills. Our aim is to cut down this preprocessing stage. Our algorithm is compared to state of the art models (Apache Nutch, BootCat, JusText), with a gold standard corpus we released. DyCorC offers a better quality of noiseless content extraction. Its algorithm is based on DOM trees with string distances, seven of which have been compared on the reference corpus, and feature-distance has been chosen as the best fit.
Article
This article tackles the problem of performing multilingual polarity classification on Twitter, comparing three techniques: (1) a multilingual model trained on a multilingual dataset, obtained by fusing existing monolingual resources, that does not need any language recognition step, (2) a dual monolingual model with perfect language detection on monolingual texts and (3) a monolingual model that acts based on the decision provided by a language identification tool. The techniques were evaluated on monolingual, synthetic multilingual and code-switching corpora of English and Spanish tweets. In the latter case we introduce the first code-switching Twitter corpus with sentiment labels. The samples are labelled according to two well-known criteria used for this purpose: the SentiStrength scale and a trinary scale (positive, neutral and negative categories). The experimental results show the robustness of the multilingual approach (1) and also that it outperforms the monolingual models on some monolingual datasets.
Article
Emotions can be judged by a combination of cues such as speech facial expressions and actions. Emotions are also articulated by text. This paper shows a new hybrid model for detecting emotion from text which depends on ontology with keywords semantic similarity. The text labelled with one of the six basic Ekman emotion categories. The main idea is to extract ontology from input sentences and match it with the ontology base which created from simple ontologies and the emotion of each ontology. The ontology extracted from the input sentence by using a triplet subject, predicate, and object extraction algorithm, then the ontology matching process is applied with the ontology base. After that the emotion of the input sentence is the emotion of the ontology which it matches with the highest score of matching. If the extracted ontology doesn't match with any ontology from the ontology base, then the keyword semantic similarity approach used. The suggested approach depends on the meaning of each sentence, the syntax and semantic analysis of the context.
Article
Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. Further progress towards understanding compositionality in tasks such as sentiment detection requires richer supervised training and evaluation resources and more powerful models of composition. To remedy this, we introduce a Sentiment Treebank. It includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment composition-ality. To address them, we introduce the Recursive Neural Tensor Network. When trained on the new treebank, this model outperforms all previous methods on several metrics. It pushes the state of the art in single sentence positive/negative classification from 80% up to 85.4%. The accuracy of predicting fine-grained sentiment labels for all phrases reaches 80.7%, an improvement of 9.7% over bag of features baselines. Lastly, it is the only model that can accurately capture the effects of negation and its scope at various tree levels for both positive and negative phrases.
Article
Social media is emerging rapidly on the internet. This media knowledge helps people, company and organizations to analyze information for important decision making. Opinion mining is also called as sentiment analysis which involves in building a system to gather and examine opinions about the product made in reviews or tweets, comments, blog posts on the web. Sentiment is classified automatically for important applications such as opinion mining and summarization. To make valuable decisions in marketing analysis where implement sentiment classification efficiently. Reviews contain sentiment which is expressed in a different way in different domains and it is costly to annotate data for each new domain. The analysis of online customer reviews in which firms cannot discover what exactly people liked and did not like in document-level and sentence-level opinion mining. So, now opinion mining ongoing research is in phrase-level opinion mining. It performs finer-grained analysis and directly looks at the opinion in online reviews. The proposed system is based on phrase-level to examine customer reviews. Phrase-level opinion mining is also well-known as aspect based opinion mining. It is used to extract most important aspects of an item and to predict the orientation of each aspect from the item reviews. The projected system implements aspect extraction using frequent itemset mining in customer product reviews and mining opinions whether it is positive or negative opinion. It identifies sentiment orientation of each aspect by supervised learning algorithms in customer reviews.
Article
Affective interaction is a new emerging area of interest for interaction designers. This research explores the potential of our hybrid approach that relies on both, lexical and machine learning techniques for detection of Ekman's six emotional categories in user's text. The initial results of the performance evaluation of the proposed hybrid approach are encouraging and comparable to related research. A demonstrative mobile application that employs the proposed approach was developed to engage the users in a dialogue that solicits their reflections on various daily events and provides appropriate affective responses.
Conference Paper
Social networks are widely used by all kinds of people to express their opinions. Predicting election outcomes is now becoming a compelling research issue. People express themselves spontaneously with respect to the social events in their social networks. Real time prediction on ongoing election events can provide feedback and trend analysis for politicians and news analysts to make informed decisions. This paper proposes an approach to predicting election results by incorporating sub-event detection and sentiment analysis in social networks to analyse as well as visualise political preferences revealed by those social network users. Extensive experiments are conducted to evaluate the performance of our approach based on a real-world Twitter dataset. Our experiments show that the proposed approach can effectively predict the election results over the given baselines.
Article
In recent years, there has been an increasing attention in the literature on the possibility of analyzing social media as a useful complement to traditional off-line polls to monitor an electoral campaign. Some scholars claim that by doing so, we can also produce a forecast of the result. Relying on a proper methodology for sentiment analysis remains a crucial issue in this respect. In this work, we apply the supervised method proposed by Hopkins and King to analyze the voting intention of Twitter users in the United States (for the 2012 Presidential election) and Italy (for the two rounds of the centre-left 2012 primaries). This methodology presents two crucial advantages compared to traditionally employed alternatives: a better interpretation of the texts and more reliable aggregate results. Our analysis shows a remarkable ability of Twitter to nowcast as well as to forecast electoral results.
Conference Paper
The web contains a wealth of product reviews, but sifting through them is a daunting task. Ideally, an opinion mining tool would process a set of search results for a given item, generating a list of product attributes (quality, features, etc.) and aggregating opinions about each of them (poor, mixed, good). We begin by identifying the unique properties of this problem and develop a method for automatically distinguishing between positive and negative reviews. Our classifier draws on information retrieval techniques for feature extraction and scoring, and the results for various metrics and heuristics vary depending on the testing situation. The best methods work as well as or better than traditional machine learning. When operating on individual sentences collected from web searches, performance is limited due to noise and ambiguity. But in the context of a complete web-based tool and aided by a simple method for grouping sentences into attributes, the results are qualitatively quite useful.
Article
Sentiment analysis is the natural language processing task dealing with sentiment detection and classification from texts. In recent years, due to the growth in the quantity and fast spreading of user-generated contents online and the impact such information has on events, people and companies worldwide, this task has been approached in an important body of research in the field. Despite different methods having been proposed for distinct types of text, the research community has concentrated less on developing methods for languages other than English. In the above-mentioned context, the present work studies the possibility to employ machine translation systems and supervised methods to build models able to detect and classify sentiment in languages for which less/no resources are available for this task when compared to English, stressing upon the impact of translation quality on the sentiment classification performance. Our extensive evaluation scenarios show that machine translation systems are approaching a good level of maturity and that they can, in combination to appropriate machine learning algorithms and carefully chosen features, be used to build sentiment analysis systems that can obtain comparable performances to the one obtained for English.
Article
Twitter messages are increasingly used to determine consumer sentiment towards a brand. The existing literature on Twitter sentiment analysis uses various feature sets and methods, many of which are adapted from more traditional text classification problems. In this research, we introduce an approach to supervised feature reduction using n-grams and statistical analysis to develop a Twitter-specific lexicon for sentiment analysis. We augment this reduced Twitter-specific lexicon with brand-specific terms for brand-related tweets. We show that the reduced lexicon set, while significantly smaller (only 187 features), reduces modeling complexity, maintains a high degree of coverage over our Twitter corpus, and yields improved sentiment classification accuracy. To demonstrate the effectiveness of the devised Twitter-specific lexicon compared to a traditional sentiment lexicon, we develop comparable sentiment classification models using SVM. We show that the Twitter-specific lexicon is significantly more effective in terms of classification recall and accuracy metrics. We then develop sentiment classification models using the Twitter-specific lexicon and the DAN2 machine learning approach, which has demonstrated success in other text classification problems. We show that DAN2 produces more accurate sentiment classification results than SVM while using the same Twitter-specific lexicon.
Conference Paper
Rapid response to a health epidemic is critical to reduce loss of life. Existing methods mostly rely on expensive surveys of hospitals across the country, typically with lag times of one to two weeks for influenza reporting, and even longer for less common diseases. In response, there have been several recently proposed solutions to estimate a population’s health from Internet activity, most notably Google’s Flu Trends service, which correlates search term frequency with influenza statistics reported by the Centers for Disease Control and Prevention (CDC). In this paper, we analyze messages posted on the micro-blogging site Twitter.com to determine if a similar correlation can be uncovered. We propose several methods to identify influenza-related messages and compare a number of regression models to correlate these messages with CDC statistics. Using over 500,000 messages spanning 10 weeks, we find that our best model achieves a correlation of.78 with CDC statistics by leveraging a document classifier to identify relevant messages.
Conference Paper
We present a novel approach to predicting the sentiment of documents in multiple languages, without translation. The only prerequisite is a multilingual parallel corpus wherein a training sample of the documents, in a single language only, have been tagged with their overall sentiment. Latent Semantic Indexing (LSI) converts that multilingual corpus into a multilingual ``concept space''. Both training and test documents can be projected into that space, allowing cross-lingual semantic comparisons between the documents without the need for translation. Accordingly, the training documents with known sentiment are used to build a machine learning model which can, because of the multilingual nature of the document projections, be used to predict sentiment in the other languages. We explain and evaluate the accuracy of this approach. We also design and conduct experiments to investigate the extent to which topic and sentiment {\em separately} contribute to that classification accuracy, and thereby shed some initial light on the question of whether topic and sentiment can be sensibly teased apart.
Article
The rapid growth in Internet applications in tourism has lead to an enormous amount of personal reviews for travel-related information on the Web. These reviews can appear in different forms like BBS, blogs, Wiki or forum websites. More importantly, the information in these reviews is valuable to both travelers and practitioners for various understanding and planning processes. An intrinsic problem of the overwhelming information on the Internet, however, is information overloading as users are simply unable to read all the available information. Query functions in search engines like Yahoo and Google can help users find some of the reviews that they needed about specific destinations. The returned pages from these search engines are still beyond the visual capacity of humans. In this research, sentiment classification techniques were incorporated into the domain of mining reviews from travel blogs. Specifically, we compared three supervised machine learning algorithms of Naïve Bayes, SVM and the character based N-gram model for sentiment classification of the reviews on travel blogs for seven popular travel destinations in the US and Europe. Empirical findings indicated that the SVM and N-gram approaches outperformed the Naïve Bayes approach, and that when training datasets had a large number of reviews, all three approaches reached accuracies of at least 80%.
Article
An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area, of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object. This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.
Article
Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, i.e., can societies experience mood states that affect their collective decision making? By extension is the public mood correlated or even predictive of economic indicators? Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time. We analyze the text content of daily Twitter feeds by two mood tracking tools, namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy). We cross-validate the resulting mood time series by comparing their ability to detect the public's response to the presidential election and Thanksgiving day in 2008. A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states, as measured by the OpinionFinder and GPOMS mood time series, are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error by more than 6%.
Serendio: Simple and practical lexicon based approach to sentiment analysis
  • P Palanisamy
  • V Yadav
  • H Elchuri
Sentiment analysis of political tweets: Towards an accurate classifier
  • A Bakliwal
  • J Foster
  • J Van Der Puil
  • R O'brien
  • L Tounsi
  • M Hughes
Cs224n final project: Sentiment analysis of news articles for financial signal prediction
  • J Zhai
  • N Cohen
  • A Atreya
Canphore: Un corpus franais pour la fouille d’ opinion cible
  • J Lark
  • E Morin
  • S Pea Saldarriaga
Supervised sentiment analysis in multilingual environments
  • D Vilares
  • M A Alonso
  • C Gmez-Rodrguez
Comparison of neural network architectures for sentiment analysis of russian tweets
  • K Arkhipenko
  • I Kozlov
  • J Trofimovich
  • K Skorniakov
  • A Gomzin
  • D Turdakov
Chapter 3-conceptual foundations of text mining and preprocessing steps
  • G Miner
  • D Delen
  • J Elder
  • A Fast
  • T Hill
  • R A Nisbet
Predicting elections from social networks based on sub-event detection and sentiment analysis
Serendio: Simple and practical lexicon based approach to sentiment analysis
  • palanisamy