Understanding the sentiment of a comment from a video or an image is an essential task in many applications. Sentiment analysis of a text can be useful for various decision-making processes. One such application is to analyse the popular sentiments of videos on social media based on viewer comments. However, comments from social media do not follow strict rules of grammar, and they contain mixing of more than one language, often written in non-native scripts. Non-availability of annotated code-mixed data for a low-resourced language like Tamil also adds difficulty to this problem. To overcome this, we created a gold standard Tamil-English code-switched, sentiment-annotated corpus containing 15,744 comment posts from YouTube. In this paper, we describe the process of creating the corpus and assigning polarities. We present inter-annotator agreement and show the results of sentiment analysis trained on this corpus as a benchmark.

Corpus creation for sentiment analysis in code-mixed Tamil-English text

Sentiment Analysis is currently considered as one of the most attractive research topics in Natural Language Processing (NLP) field. The main objective of sentiment analysis is to identify the opinions and emotions of the users through written contents. While there are different studies that have approached this field using various techniques, it is still considered a challenging topic with many difficulties that are yet to be solved, such as having modern accents, slang words, spelling and grammatical mistakes, and other issues that cannot be overcome with traditional methods and sentiment lexicons. In this work, we propose a hybrid machine learning approach to enhance sentiment analysis; as we build a classification model based on three classes, which are positive, neutral, and negative emotions, using Support Vector Machines (SVM) classifier, while combining two feature selection techniques using the ReliefF and Multi-Verse Optimizer (MVO) algorithms. We also extract more than 6900 tweets from Twitter social network to test our work. Our hybrid method is compared against other classifiers and methods in terms of accuracy. Results show that our proposed method outperforms other techniques and classifiers, by obtaining better results in most of the datasets while reducing the number of features by up to 96.85% from the original feature set. We also categorize the extracted features into Objective, Subjective and Emoticon words to analyze them during the first and the final feature selection processes and find any existing relations. Very similar results are obtained by both feature selection techniques; due to a number of factors that are explained in this paper.

An efficient hybrid filter and evolutionary wrapper approach for sentiment analysis of various topics on Twitter

Natural language processing has been studied for many years, and it has been applied to many researches and commercial applications. A new model is proposed in this paper, and is used in the English document-level emotional classification. In this survey, we proposed a new model by using an ID3 algorithm of a decision tree to classify semantics (positive, negative, and neutral) for the English documents. The semantic classification of our model is based on many rules which are generated by applying the ID3 algorithm to 115,000 English sentences of our English training data set. We test our new model on the English testing data set including 25,000 English documents, and achieve 63.6% accuracy of sentiment classification results.

A decision tree using ID3 algorithm for English semantic analysis

/pdf/proceedings-of-the-2015-conference-of-the-north-american-3qbnr7bvco.pdf

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

The solutions for processing sentiment analysis are very important and very helpful for many researchers, many applications, etc. This new model has been proposed in this paper, used in the English document-level sentiment classification. In this research, we propose a new model using C4.5 Algorithm of a decision tree to classify semantics (positive, negative, neutral) for the English documents. Our English training data set has 140,000 English sentences, including 70,000 English positive sentences and 70,000 English negative sentences. We use the C4.5 algorithm on the 70,000 English positive sentences to generate a decision tree and many association rules of the positive polarity are created by the decision tree. We also use the C4.5 algorithm on the 70,000 English negative sentences to generate a decision tree and many association rules of the negative polarity are created by the decision tree. Classifying sentiments of one English document is identified based on the association rules of the positive polarity and the negative polarity. Our English testing data set has 25,000 English documents, including 12,500 English positive reviews and 12,500 English negative reviews. We have tested our new model on our testing data set and we have achieved 60.3% accuracy of sentiment classification on this English testing data set.

/pdf/a-c4-5-algorithm-for-english-emotional-classification-2k7ami4beu.pdf

A C4.5 algorithm for english emotional classification

This paper describes the system we used for Shared Task on Sentiment Analysis in Indian Languages SAIL Tweets, at MIKE-2015. Twitter is one of the most popular platform which allows users to share their opinion in the form of tweets. Since it restricts the users with 140 characters, the tweets are actually very short to carry opinions and sentiments to analyze. We take the help of a twitter training dataset in Indian Language Hindi and apply data mining approaches for analyzing the sentiments. We used a state-of-the-art Data Mining tool Weka to automatically classify the sentiment of Hindi tweets into positive, negative or neutral.

Sentiment Classification: An Approach for Indian Language Tweets Using Decision Tree

Users of the WWW across the globe are increasing rapidly. According to Internet live stats there are more than 3 billion Internet users worldwide today and the number of non-English native speakers is quite high there. A large proportion of these non-English speakers access the Internet in their native languages but use the Roman script to express themselves through various communication channels like messages and posts. With the advent of Web 2.0, user-generated content is increasing on the Web at a very rapid rate. A substantial proportion of this content is transliterated data. To leverage this huge information repository, there is a matching effort to process transliterated text. In this article, we survey the recent body of work in the field of transliteration. We start with a definition and discussion of the different types of transliteration followed by various deterministic and non-deterministic approaches used to tackle transliteration-related issues in machine translation and information retrieval. Finally, we study the performance of those techniques and present a comparative analysis of them.

/pdf/machine-transliteration-and-transliterated-text-retrieval-a-1orw8s7vlv.pdf

Machine transliteration and transliterated text retrieval: a survey

This paper presents a proposed work for extracting the sentiments from tweets in Indian Language. We proposed a system that deal with the goal to extract the sentiments from Bengali & Tamil tweets. Our aim is to classify a given Bengali or Tamil tweets into three sentiment classes namely positive, negative or neutral. In recent time, Twitter gain much attention to NLP researchers as it is most widely used platform that allows the user to share there opinion in form of tweets. The proposed methodology used unigram and bi-gram models along with different supervised machine learning techniques. We also consider the use of features generated from lexical resources such as Wordnets and Emoticons Tagger.

Sentiment mining: An approach for Bengali and Tamil tweets

This paper describes the approach we adopted during official submission of FIRE-2013 Shared Task on Transliterated Search along with few other approaches that we experimented post-submission. The techniques solve the problem of language labeling, by identifying query word as English or Hindi (E or H) term in mixed language sentence queries. Manual and machine learning algorithms are used. For the transliteration of H labeled word we use manual (dictionary based), generative (grapheme based) and combination of both in different algorithms. We observe that learning based classification improves labeling accuracy. Extraction based transliteration gives better result than Generation based when the terms are available in bilingual dictionary. But it may lead to incorrect transliteration if terms are wrongly aligned and the approach fails for out-of-dictionary words. In this case transliteration by generation is the only alternative. But generation alone does not perform well because of spelling variation in transliterated terms. During evaluation we also observe that transliteration systems are generally corpus-biased. Although our performance in the official submission was moderate, we obtain better results during our post-submission experiments.

ISM@FIRE-2013 Shared Task on Transliterated Search

This paper describes the approaches we have adopted to identify the classes of named entities and annotate them with proper tags. Named Entity Recognition (NER) is a subtask of information extraction that seeks to locate and classify the entity names (proper nouns) in a text. NER systems are useful in many Natural Language Processing (NLP) applications such as question answering, machine translation, information extraction and so on. IN this task, Conditional Random Field (CRF) is used for the classification where tokens are classified hierarchically. We discuss two approaches: one for the official submission and the other its extended version. The performance of our systems were moderate.

Dinesh Kumar Prabhakar

Papers

Sentiment Classification: An Approach for Indian Language Tweets Using Decision Tree

Machine transliteration and transliterated text retrieval: a survey

Sentiment mining: An approach for Bengali and Tamil tweets

ISM@FIRE-2013 Shared Task on Transliterated Search

ISM@FIRE-2014: Named Entity Recognition for Indian Languages