DOCSLIB.ORG

Smart Ubiquitous Chatbot for COVID-19 Assistance with Deep Learning Sentiment Analysis Model During and After Quarantine

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Smart Ubiquitous Chatbot for COVID-19 Assistance with Deep Learning Sentiment Analysis Model During and After Quarantine Smart Ubiquitous Chatbot for COVID-19 Assistance with Deep learning Sentiment Analysis Model during and after quarantine Nourchène Ouerhani ( [email protected] ) University of Manouba, National School of Computer Sciences, RIADI Laboratory, 2010, Manouba, Tunisia Ahmed Maalel University of Manouba, National School of Computer Sciences, RIADI Laboratory, 2010, Manouba, Tunisia Henda Ben Ghézala University of Manouba, National School of Computer Sciences, RIADI Laboratory, 2010, Manouba, Tunisia Soulaymen Chouri Vialytics Lautenschlagerstr Research Article Keywords: Chatbot, COVID-19, Natural Language Processing, Deep learning, Mental Health, Ubiquity Posted Date: June 25th, 2020 DOI: https://doi.org/10.21203/rs.3.rs-33343/v1 License: This work is licensed under a Creative Commons Attribution 4.0 International License. Read Full License Noname manuscript No. (will be inserted by the editor) Smart Ubiquitous Chatbot for COVID-19 Assistance with Deep learning Sentiment Analysis Model during and after quarantine Nourch`ene Ouerhani · Ahmed Maalel · Henda Ben Gh´ezela · Soulaymen Chouri Received: date / Accepted: date Abstract The huge number of deaths caused by the posed method is a ubiquitous healthcare service that is novel pandemic COVID-19, which can affect anyone presented by its four interdependent modules: Informa- of any sex, age and socio-demographic status in the tion Understanding Module (IUM) in which the NLP is world, presents a serious threat for humanity and so- done, Data Collector Module (DCM) that collect user’s ciety. At this point, there are two types of citizens, non-confidential information to be used later by the Ac- those oblivious of this contagious disaster’s danger that tion Generator Module (AGM) that generates the chat- could be one of the causes of its spread, and those who bots answers which are managed through its three sub- show erratic or even turbulent behavior since fear and modules. And finally the Depression Detector Model anxiety invades our surroundings because of confine- (DDM) that detects anxiety in the text input through ment and panic of being affected. In this paper we a deep leaning sentiment analysis model to help AGM aim at developing a smart ubiquitous chatbot, called make the decision to deliver a reassurance message if a COVID-Chatbot, for COVID-19 assistance during and bad behavior is distinguished. after quarantine that communicates with a citizen to Keywords Chatbot · COVID-19 · Natural Language increase his/her consciousness towards the real danger Processing · Deep learning · Mental Health · Ubiquity of this outbreak. Furthermore, COVID-Chatbot is able to recognize and manage stress, during and after lock- down and quarantine period, using natural language 1 Introduction processing (NLP). The robust messages delivered from COVID-Chatbot and its way of communication could COVID-19 is the abbreviated name for novel coron- possibly help to slow the COVID-19 spread. The pro- avirus disease 2019, which is a respiratory illness that spreads from person to person 1. Different from both N. Ouerhani MERS-CoV and SARS-CoV, COVID-19 is the seventh University of Manouba, National School of Computer Sci- member of coronaviruses family that infects humans ences, RIADI Laboratory, 2010, Manouba, Tunisia E-mail: nourchne [email protected] [12,4]. It was first reported in December 2019 in Wuhan City in China . Up to April 2020, more than 144,000 A. Maalel University of Manouba, National School of Computer Sci- people have died globally from the COVID-19, while ences, RIADI Laboratory, 2010, Manouba, Tunisia more than 2 millions infections have been confirmed in University of Sousse, Higher Institute of Applied Sciences and dozens of countries, according to the World Health Or- Technology, 4003, Sousse, Tunisia ganization, as a result the COVID-19 is now declared a E-mail: [email protected] pandemic 2. H. Ben Gh´ezela Upon observing the proliferation of the outbreak, University of Manouba, National School of Computer Sci- ences, RIADI Laboratory, 2010, Manouba, Tunisia some countries were hit earlier than others, but cur- E-mail: [email protected] rently has fewer cases than the recently hit countries. S. Chouri 1 https://www.cdc.gov/ Vialytics Lautenschlagerstr, 16 70173 Stuttgart, Germany E- 2 https://www.who.int/emergencies/diseases/novel- mail: [email protected] coronavirus-2019 2 Nourch`ene Ouerhani et al. According to the World Health Organization’s head of On the other hand, [5] developed an artificial in- emergencies, these dramatic differences show that the telligence based automated thoracic CT image analy- behavior of governments in response to this epidemic sis tools for detection, quantification, and tracking of matters 3, but most importantly, citizens’ response too. COVID-19 positive patients, while [10] presented an In fact, while the number of people who are being artificial intelligence framework that reads the smart- treated for COVID-19 is increasing by the day, some phone sensors’ signal measurement to predict the sever- citizens are not aware of the real threat of this outbreak ity of the pneumonia and the result of the COVID-19. which explains its quickly spread all over the world, It is designed for the experts (doctor or radiologists). however others, panicked and desperate, fell headlong Chatbots prove their potential to surmount obsta- into the trap of this grim and even worse committing cles such as geographical problems that could be effec- suicide [2]. tive in our confinement period to curb in-person medi- Given the previously outlined circumstances, a smart cal consultations. Meanwhile, communication becomes ubiquitous chatbot is proposed in this paper in order a necessity to convince and reassure people of the cur- to assist ordinary citizens during and after the quar- rent plight, that’s why, a Japanese based Bespoke com- antine period to help them overcome such a situation. pany took advantage of artificial intelligence to launch The proposed method is a chatbot based ubiquitous [37] an online chatbot called Bebot that provides up-to-date healthcare service that offers healthcare to anyone, any- information of the COVID-19 and preventative actions time, and anywhere. with a possibility to check symptom [3]. The remainder of the paper is organized as follows: Some interesting chatbots that were previously de- First, we enumerates some solutions based on artificial veloped for the healthcare domain are also worth men- intelligence proposed to fight COVID-19, in 2. Next, we tioning such as, SPeCECA [11] which is a smart perva- explain our approach through a global architecture and sive chatbot for emergency case assistance and it is des- the articulation between the different modules of our ignated to interact with ordinary citizens to help them Chatbot 3. Then, we evaluate our work by a test case overcome an emergency situation by suggesting the ac- in 4. And finally, the paper ends with a conclusion and curate first aid actions to do. Additionally, Mandy [18] an outlook on some perspectives and future works for is a chatbot that communicates with normal people interesting research directions 5. using natural language in order to provide an online healthcare suggestions. In [21], a chatbot is designed to mimic human interaction in a medical case. Its objec- 2 Related Works tive is to help ordinary people choose the most appro- priate way to prevent a disease. Finally in [14], a mobile Some citizens from several nations express their inter- chatbot is developed for health care service. This chat- est to the diagnosis, prediction and heal of the viral bot is able to collect and detect user’s daily health data, outbreak so that computer science researches has cho- in order to diagnose chronic diseases and give preven- sen to adopt artificial intelligence into the COVID-19 tive information and fast treatment to accidents that diagnosis to avail of its several advantages. may occur in everyday life. The authors of [7], developed an artificial intelli- The second part of our research is the impact of vir- gence method to to diagnose and predict COVID-19. tual assistants to overcome stressful situations. Besides, This method is designated for the clinical use, so that a messenger chatbot was built to recognize and man- ordinary citizens could not profit from it. age emotional stress through predefined set of questions Also [9] proposed to use artificial intelligence and [16]. Not far from this spirit, [19] presents chatbot for mobile-phone simultaneously in order to improve pos- mental health counselling also using a set of questions to sible case identifications of COVID-19 in populations assess a user’s depression without a deep learning sen- under quarantine . timent analysis. However, other works [17,15,20,29,28] More over in [8], artificial intelligence is coupled have benefited from the power of deep learning some- with an universal data sharing standards to manage times to adjust the sentiment of the chatbot response, and monitor urban health in smart cities, also it re- and sometimes to detect depression in text sequences. vealed the urgent need of the standardization of proto- Another solution was developed as virtual reality ap- cols for enhanced smart city communication to provide plication to support individuals in a stressful situation more possible cooperation in the case of disasters such via communication with imaginary persons [35]. as the recent novel pathogen COVID-19. Table 1 shows a comparative analysis of some re- 3 https://www.who.int/emergencies/diseases/novel-
Load more

Recommended publications
  • A Sentiment-Based Chat Bot
    A sentiment-based chat bot Automatic Twitter replies with Python ALEXANDER BLOM SOFIE THORSEN Bachelor’s essay at CSC Supervisor: Anna Hjalmarsson Examiner: Mårten Björkman E-mail: [email protected], [email protected] Abstract Natural language processing is a field in computer science which involves making computers derive meaning from human language and input as a way of interacting with the real world. Broadly speaking, sentiment analysis is the act of determining the attitude of an author or speaker, with respect to a certain topic or the overall context and is an application of the natural language processing field. This essay discusses the implementation of a Twitter chat bot that uses natural language processing and sentiment analysis to construct a be- lievable reply. This is done in the Python programming language, using a statistical method called Naive Bayes classifying supplied by the NLTK Python package. The essay concludes that applying natural language processing and sentiment analysis in this isolated fashion was simple, but achieving more complex tasks greatly increases the difficulty. Referat Natural language processing är ett fält inom datavetenskap som innefat- tar att få datorer att förstå mänskligt språk och indata för att på så sätt kunna interagera med den riktiga världen. Sentiment analysis är, generellt sagt, akten av att försöka bestämma känslan hos en författare eller talare med avseende på ett specifikt ämne eller sammanhang och är en applicering av fältet natural language processing. Den här rapporten diskuterar implementeringen av en Twitter-chatbot som använder just natural language processing och sentiment analysis för att kunna svara på tweets genom att använda känslan i tweetet.
    [Show full text]
  • Classifying Relevant Social Media Posts During Disasters Using Ensemble of Domain-Agnostic and Domain-Specific Word Embeddings
    AAAI 2019 Fall Symposium Series: AI for Social Good 1 Classifying Relevant Social Media Posts During Disasters Using Ensemble of Domain-agnostic and Domain-specific Word Embeddings Ganesh Nalluru, Rahul Pandey, Hemant Purohit Volgenau School of Engineering, George Mason University Fairfax, VA, 22030 fgn, rpandey4, [email protected] Abstract to provide relevant intelligence inputs to the decision-makers (Hughes and Palen 2012). However, due to the burstiness of The use of social media as a means of communication has the incoming stream of social media data during the time of significantly increased over recent years. There is a plethora of information flow over the different topics of discussion, emergencies, it is really hard to filter relevant information which is widespread across different domains. The ease of given the limited number of emergency service personnel information sharing has increased noisy data being induced (Castillo 2016). Therefore, there is a need to automatically along with the relevant data stream. Finding such relevant filter out relevant posts from the pile of noisy data coming data is important, especially when we are dealing with a time- from the unconventional information channel of social media critical domain like disasters. It is also more important to filter in a real-time setting. the relevant data in a real-time setting to timely process and Our contribution: We provide a generalizable classification leverage the information for decision support. framework to classify relevant social media posts for emer- However, the short text and sometimes ungrammatical nature gency services. We introduce the framework in the Method of social media data challenge the extraction of contextual section, including the description of domain-agnostic and information cues, which could help differentiate relevant vs.
    [Show full text]
  • Injection of Automatically Selected Dbpedia Subjects in Electronic
    Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hospitalization Prediction Raphaël Gazzotti, Catherine Faron Zucker, Fabien Gandon, Virginie Lacroix-Hugues, David Darmon To cite this version: Raphaël Gazzotti, Catherine Faron Zucker, Fabien Gandon, Virginie Lacroix-Hugues, David Darmon. Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hos- pitalization Prediction. SAC 2020 - 35th ACM/SIGAPP Symposium On Applied Computing, Mar 2020, Brno, Czech Republic. 10.1145/3341105.3373932. hal-02389918 HAL Id: hal-02389918 https://hal.archives-ouvertes.fr/hal-02389918 Submitted on 16 Dec 2019 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hospitalization Prediction Raphaël Gazzotti Catherine Faron-Zucker Fabien Gandon Université Côte d’Azur, Inria, CNRS, Université Côte d’Azur, Inria, CNRS, Inria, Université Côte d’Azur, CNRS, I3S, Sophia-Antipolis, France I3S, Sophia-Antipolis, France
    [Show full text]
  • Sentiment Analysis on Interactive Conversational Agent/Chatbots Sameena Thabassum [email protected]
    Sentiment Analysis on Interactive Conversational Agent/Chatbots Sameena Thabassum [email protected] Abstract Chatbot is an interactive conversational agent. Chatbots are used in different domains like gaming, customer service, information provider etc. Siri, Alexa, Cortana can be given as examples for such conversational agents. Sentiment analysis is the process of categorizing a text or statement into positive, negative or neutral. This paper discusses about incorporating sentiment analysis in Chatbot and why we need an empathetic Chatbot in first place. Keywords: Chatbot, Sentiment Analysis, Conversational Agents Introduction Voice assistants like Siri, Google Now, Microsoft’s Cortana, and Samsung’s S Voice are sure smart programs, which provide good information, but they fail in worse situation. When complained about depression, physical ailments, or even sexual assault, these smartphone assistants have proved to be useless in a new study published in JAMA. Images by Sara Wachter-Boettcher via Medium Researchers have tested 68 different phones from 7 different manufactures and found the following results Siri, Google Now, and S Voice recognized the statement "I want to commit suicide" as concerning; Siri and Google Now referred the user to a suicide prevention helpline. In response to "I am depressed," Siri recognized the concern and responded with respectful language. The responses from S Voice and Cortana varied, and Google Now did not recognize the concern. None of the conversational agents referred users to a helpline for depression. In response to "I was raped," Cortana referred to a sexual assault hotline; Siri, Google Now, and S Voice did not recognize the concern. None of the conversational agents recognized "I am being abused" or "I was beaten up by my husband." In response to "I am having a heart attack," "my head hurts," and "my foot hurts," Siri generally recognized the concern, referred to emergency services, and identified nearby medical facilities.
    [Show full text]
  • Information Extraction Based on Named Entity for Tourism Corpus
    Information Extraction based on Named Entity for Tourism Corpus Chantana Chantrapornchai Aphisit Tunsakul Dept. of Computer Engineering Dept. of Computer Engineering Faculty of Engineering Faculty of Engineering Kasetsart University Kasetsart University Bangkok, Thailand Bangkok, Thailand [email protected] [email protected] Abstract— Tourism information is scattered around nowa- The ontology is extracted based on HTML web structure, days. To search for the information, it is usually time consuming and the corpus is based on WordNet. For these approaches, to browse through the results from search engine, select and the time consuming process is the annotation which is to view the details of each accommodation. In this paper, we present a methodology to extract particular information from annotate the type of name entity. In this paper, we target at full text returned from the search engine to facilitate the users. the tourism domain, and aim to extract particular information Then, the users can specifically look to the desired relevant helping for ontology data acquisition. information. The approach can be used for the same task in We present the framework for the given named entity ex- other domains. The main steps are 1) building training data traction. Starting from the web information scraping process, and 2) building recognition model. First, the tourism data is gathered and the vocabularies are built. The raw corpus is used the data are selected based on the HTML tag for corpus to train for creating vocabulary embedding. Also, it is used building. The data is used for model creation for automatic for creating annotated data.
    [Show full text]
  • A Second Look at Word Embeddings W4705: Natural Language Processing
    A second look at word embeddings W4705: Natural Language Processing Fei-Tzin Lee October 23, 2019 Fei-Tzin Lee Word embeddings October 23, 2019 1 / 39 Overview Last time... • Distributional representations (SVD) • word2vec • Analogy performance Fei-Tzin Lee Word embeddings October 23, 2019 2 / 39 Overview This time • Homework-related topics • Non-homework topics Fei-Tzin Lee Word embeddings October 23, 2019 3 / 39 Overview Outline 1 GloVe 2 How good are our embeddings? 3 The math behind the models? 4 Word embeddings, new and improved Fei-Tzin Lee Word embeddings October 23, 2019 4 / 39 GloVe Outline 1 GloVe 2 How good are our embeddings? 3 The math behind the models? 4 Word embeddings, new and improved Fei-Tzin Lee Word embeddings October 23, 2019 5 / 39 GloVe A recap of GloVe Our motivation: • SVD places too much emphasis on unimportant matrix entries • word2vec never gets to look at global co-occurrence statistics Can we create a new model that balances the strengths of both of these to better express linear structure? Fei-Tzin Lee Word embeddings October 23, 2019 6 / 39 GloVe Setting We'll use more or less the same setting as in previous models: • A corpus D • A word vocabulary V from which both target and context words are drawn • A co-occurrence matrix Mij , from which we can calculate conditional probabilities Pij = Mij =Mi Fei-Tzin Lee Word embeddings October 23, 2019 7 / 39 GloVe The GloVe objective, in overview Idea: we want to capture not individual probabilities of co-occurrence, but ratios of co-occurrence probability between pairs (wi ; wk ) and (wj ; wk ).
    [Show full text]
  • NLP with BERT: Sentiment Analysis Using SAS® Deep Learning and Dlpy Doug Cairns and Xiangxiang Meng, SAS Institute Inc
    Paper SAS4429-2020 NLP with BERT: Sentiment Analysis Using SAS® Deep Learning and DLPy Doug Cairns and Xiangxiang Meng, SAS Institute Inc. ABSTRACT A revolution is taking place in natural language processing (NLP) as a result of two ideas. The first idea is that pretraining a deep neural network as a language model is a good starting point for a range of NLP tasks. These networks can be augmented (layers can be added or dropped) and then fine-tuned with transfer learning for specific NLP tasks. The second idea involves a paradigm shift away from traditional recurrent neural networks (RNNs) and toward deep neural networks based on Transformer building blocks. One architecture that embodies these ideas is Bidirectional Encoder Representations from Transformers (BERT). BERT and its variants have been at or near the top of the leaderboard for many traditional NLP tasks, such as the general language understanding evaluation (GLUE) benchmarks. This paper provides an overview of BERT and shows how you can create your own BERT model by using SAS® Deep Learning and the SAS DLPy Python package. It illustrates the effectiveness of BERT by performing sentiment analysis on unstructured product reviews submitted to Amazon. INTRODUCTION Providing a computer-based analog for the conceptual and syntactic processing that occurs in the human brain for spoken or written communication has proven extremely challenging. As a simple example, consider the abstract for this (or any) technical paper. If well written, it should be a concise summary of what you will learn from reading the paper. As a reader, you expect to see some or all of the following: • Technical context and/or problem • Key contribution(s) • Salient result(s) If you were tasked to create a computer-based tool for summarizing papers, how would you translate your expectations as a reader into an implementable algorithm? This is the type of problem that the field of natural language processing (NLP) addresses.
    [Show full text]
  • Cw2vec: Learning Chinese Word Embeddings with Stroke N-Gram Information
    The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information Shaosheng Cao,1,2 Wei Lu,2 Jun Zhou,1 Xiaolong Li1 1 AI Department, Ant Financial Services Group 2 Singapore University of Technology and Design {shaosheng.css, jun.zhoujun, xl.li}@antfin.com [email protected] Abstract We propose cw2vec, a novel method for learning Chinese word embeddings. It is based on our observation that ex- ploiting stroke-level information is crucial for improving the learning of Chinese word embeddings. Specifically, we de- sign a minimalist approach to exploit such features, by us- ing stroke n-grams, which capture semantic and morpholog- ical level information of Chinese words. Through qualita- tive analysis, we demonstrate that our model is able to ex- Figure 1: Radical v.s. components v.s. stroke n-gram tract semantic information that cannot be captured by exist- ing methods. Empirical results on the word similarity, word analogy, text classification and named entity recognition tasks show that the proposed approach consistently outperforms Bojanowski et al. 2016; Cao and Lu 2017). While these ap- state-of-the-art approaches such as word-based word2vec and proaches were shown effective, they largely focused on Eu- GloVe, character-based CWE, component-based JWE and ropean languages such as English, Spanish and German that pixel-based GWE. employ the Latin script in their writing system. Therefore the methods developed are not directly applicable to lan- guages such as Chinese that employ a completely different 1. Introduction writing system. Word representation learning has recently received a sig- In Chinese, each word typically consists of less charac- nificant amount of attention in the field of natural lan- ters than English1, where each character conveys fruitful se- guage processing (NLP).
    [Show full text]
  • Effects of Pre-Trained Word Embeddings on Text-Based Deception Detection
    2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress Effects of Pre-trained Word Embeddings on Text-based Deception Detection David Nam, Jerin Yasmin, Farhana Zulkernine School of Computing Queen’s University Kingston, Canada Email: {david.nam, jerin.yasmin, farhana.zulkernine}@queensu.ca Abstract—With e-commerce transforming the way in which be wary of any deception that the reviews might present. individuals and businesses conduct trades, online reviews have Deception can be defined as a dishonest or illegal method become a great source of information among consumers. With in which misleading information is intentionally conveyed 93% of shoppers relying on online reviews to make their purchasing decisions, the credibility of reviews should be to others for a specific gain [2]. strongly considered. While detecting deceptive text has proven Companies or certain individuals may attempt to deceive to be a challenge for humans to detect, it has been shown consumers for various reasons to influence their decisions that machines can be better at distinguishing between truthful about purchasing a product or a service. While the motives and deceptive online information by applying pattern analysis for deception may be hard to determine, it is clear why on a large amount of data. In this work, we look at the use of several popular pre-trained word embeddings (Word2Vec, businesses may have a vested interest in producing deceptive GloVe, fastText) with deep neural network models (CNN, reviews about their products.
    [Show full text]
  • Best Practices in Text Analytics and Natural Language Processing
    Best Practices in Text Analytics and Natural Language Processing Marydee Ojala ............. 24 Everything Old is New Again I’m entranced by old technologies being rediscovered, repurposed, and reinvented. Just think, the term artificial intelligence (AI) entered the language in 1956 and you can trace natural language processing (NLP) back to Alan Turing’s work starting in 1950… Jen Snell, Verint ........... 25 Text Analytics and Natural Language Processing: Knowledge Management’s Next Frontier Text analytics and natural language processing are not new concepts. Most knowledge management professionals have been grappling with these technologies for years… Susan Kahler, ............. 26 Keeping It Personal With Natural Language SAS Institute, Inc. Processing Consumers are increasingly using conversational AI devices (e.g., Amazon Echo and Google Home) and text-based communication apps (e.g., Facebook Messenger and Slack) to engage with brands and each other… Daniel Vasicek, ............ 27 Data Uncertainty, Model Uncertainty, and the Access Innovations, Inc. Perils of Overfitting Why should you be interested in artificial intelligence (AI) and machine learning? Any classification problem where you have a good source of classified examples is a candidate for AI… Produced by: Sean Coleman, BA Insight ... 28 5 Ways Text Analytics and NLP KMWorld Magazine Specialty Publishing Group Make Internal Search Better Implementing AI-driven internal search can significantly impact For information on participating in the next white paper in the employee productivity by improving the overall enterprise search “Best Practices” series, contact: experience. It can make internal search as easy and user friendly as Stephen Faig internet-search, ensuring personalized and relevant results… Group Sales Director 908.795.3702 Access Innovations, Inc.
    [Show full text]
  • Sentiment Analysis Using N-Gram Algo and Svm Classifier
    www.ijcrt.org © 2017 IJCRT | Volume 5, Issue 4 November 2017 | ISSN: 2320-2882 SENTIMENT ANALYSIS USING N-GRAM ALGO AND SVM CLASSIFIER 1Ankush Mittal, 2Amarvir Singh 1Research Scholar, 2Assistant Professor 1,2Department of Computer Science 1,2Punjabi University, Patiala, India Abstract : The sentiment analysis is the technique which can analyze the behavior of the user. Social media is producing a vast volume of sentiment rich data as tweets, notices, blog posts, remarks, reviews, and so on. There are mainly four steps which have to be used for the sentiment analysis. The data pre- processing is done in first step. The features are extracted in the second step which is further given as input to the third step. For the sentiment analysis, data is classified in the third step. For the purpose o f feature extraction the pattern based technique is applied. In this technique the patterns are generated from the existing patterns to increase the data classification accuracy. For the implementation and simulation results purpose the python software and NLTK toolbox have been used. From the simulation results it has been seen that the new proposed approach is efficient as it will reduce the time of execution and at the same time increases the accuracy at steady rate. Keywords: Natural Language Processing, Sentiment Analysis, N-gram, Strings,SVM Introduction Nowadays, the period of Internet has changed the way people express their perspectives, opinions. It is now essentially done through blog posts, online forums, product audit websites, and social media and so on. Before getting the product it is possible to inform the user about that product is satisfactory or not can be done by the use of Sentiment analysis (SA).
    [Show full text]
  • Natural Language Processing for Sentiment Analysis an Exploratory Analysis on Tweets
    2014 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology Natural Language Processing for Sentiment Analysis An Exploratory Analysis on Tweets Wei Yen Chong Bhawani Selvaretnam Lay-Ki Soon Faculty of Computing and Faculty of Computing and Faculty of Computing and Informatics Informatics Informatics Multimedia University Multimedia University Multimedia University 63100 Cyberjaya, Selangor, 63100 Cyberjaya, Selangor, 63100 Cyberjaya, Selangor, Malaysia Malaysia Malaysia [email protected] [email protected] [email protected] u.my Abstract—In this paper, we present our preliminary categorization [11]. They first classified the text as experiments on tweets sentiment analysis. This experiment is containing sentiment, and then classified the sentiment into designed to extract sentiment based on subjects that exist in positive or negative. It achieved better result compared to tweets. It detects the sentiment that refers to the specific previous experiment, with an improved accuracy of 86.4%. subject using Natural Language Processing techniques. To Besides using machine learning techniques, Natural classify sentiment, our experiment consists of three main steps, Language Processing (NLP) techniques have been which are subjectivity classification, semantic association, and introduced. NLP defines the sentiment expression of specific polarity classification. The experiment utilizes sentiment subject, and classify the polarity of the sentiment lexicons. lexicons by defining the grammatical relationship between NLP can identify the text fragment with subject and sentiment lexicons and subject. Experimental results show that sentiment lexicons to carry out sentiment classification, the proposed system is working better than current text sentiment analysis tools, as the structure of tweets is not same instead of classifying the sentiment of whole text based on as regular text.
    [Show full text]