Braja Gopal Patra

Shared Task on Sentiment Analysis in Indian Languages SAIL Tweets - An Overview

Sentiment Analysis in Twitter has been considered as a vital task for a decade from various academic and commercial perspectives. Several works have been performed on Twitter sentiment analysis or opinion mining for English in contrast to the Indian languages. Here, we summarize the objectives and evaluation of the sentiment analysis task in tweets for three Indian languages namely Bengali, Hindi and Tamil. This is the first attempt to sentiment analysis task in the context of Indian language tweets. The main objective of this task was to classify the tweets into positive, negative, and neutral polarity. For training and testing purpose, the tweets from each language were provided. Each of the participating teams was asked to submit two systems, constrained and unconstrained systems for each of the languages. We ranked the systems based on the accuracy of the systems. Total of six teams submitted the results and the maximum accuracy achieved for Bengali, Hindi, and Tamil are 43.2i¾?%, 55.67i¾?%, and 39.28i¾?% respectively.

Unsupervised Approach to Hindi Music Mood Classification

We often choose to listen to a song that suits our mood at that instant because an intimate relationship presents between music and human emotions. Thus, the automatic methods are needed to classify music by moods that have gained a lot of momentum in the recent years. It helps in creating library, searching music and other related application. Several studies on Music Information Retrieval (MIR) have also been carried out in recent decades. In the present task, we have built an unsupervised classifier for Hindi music mood classification using different audio related features like rhythm, timber and intensity. The dataset used in our experiment is manually prepared by five annotators and is composed of 250 Hindi music clips of 30 seconds that consist of five mood clusters. The accuracy achieved for music mood classification on the above data is 48%.

JU_CSE: A Conditional Random Field (CRF) Based Approach to Aspect Based Sentiment Analysis

The fast upswing of online reviews and their sentiments on the Web became very useful information to the people. Thus, the opinion/sentiment mining has been adopted as a subject of increasingly research interest in the recent years. Being a participant in the Shared Task Challenge, we have developed a Conditional Random Field based system to accomplish the Aspect Based Sentiment Analysis task. The aspect term in a sentence is defined as the target entity. The present system identifies aspect term, aspect categories and their sentiments from the Laptop and Restaurants review datasets provided by the organizers.

JU_NLP at SemEval-2016 Task 6: Detecting Stance in Tweets using Support Vector Machines.

We describe the system submitted to the SemEval-2016 for detecting stance in tweets (Task 6, Subtask A). One of the main goals of stance detection is to automatically determine the stance of a tweet towards a specific target as ‘FAVOR’, ‘AGAINST’, or ‘NONE’. We developed a supervised system using Support Vector Machines to identify the stance by analyzing various lexical and semantic features. The average F1 score achieved by our system is 60.60.

Labeling data and developing supervised framework for hindi music mood analysis

Digitization has created a wide platform for music, in the form of televisions, desktops and other hand held devices. This has increased the reach of musical content as well as its impact on people. Music is often associated with distinct emotional content, generally referred to as music mood. Literature focusing on analyzing the content of a music piece, often discusses music mood as an important metadata. The present article addresses the issue of Hindi music mood classification by considering important issues like taxonomy development, annotation and automated mood classification. We annotated a total of 1540 music clips of 60 seconds duration each, with either of a proposed set of five mood classes derived from Russell’s circumplex model. We developed several supervised systems with the help of different classification algorithms and neural networks such as Support Vector Machines, Decision Trees, and Feed Forward Neural Networks. Our experiments reveal that features like timbre, rhythm, and intensity are associated with enhanced classification accuracy. Overall, the results were found satisfactory and Feed Forward Neural Networks based system achieved the maximum F-measure of 0.725 based on 10-fold cross validation.

JU_NLP at SemEval-2016 Task 11: Identifying Complex Words in a Sentence.

The complex word identification task refers to the process of identifying difficult words in a sentence from the perspective of readers belonging to a specific target audience. This task has immense importance in the field of lexical simplification. Lexical simplification helps in improving the readability of texts consisting of challenging words. As a participant of the SemEval-2016: Task 11 shared task, we developed two systems using various lexical and semantic features to identify complex words, one using Naive Bayes and another based on Random Forest Classifiers. The Naive Bayes classifier based system achieves the maximum G-score of 76.7% after incorporating rule based post-processing techniques.

A Multilevel Approach to Sentiment Analysis of Figurative Language in Twitter

Commendable amount of work has been attempted in the field of Sentiment Analysis or Opinion Mining from natural language texts and Twitter texts. One of the main goals in such tasks is to assign polarities (positive or negative) to a piece of text. But, at the same time, one of the important as well as difficult issues is how to assign the degree of positivity or negativity to certain texts. The answer becomes more complex when we perform a similar task on figurative language texts collected from Twitter. Figurative language devices such as irony and sarcasm contain an intentional secondary or extended meaning hidden within the expressions. In this paper we present a novel approach to identify the degree of the sentiment (fine grained in an 11-point scale) for the figurative language texts. We used several semantic features such as sentiment and intensifiers as well as we introduced sentiment abruptness, which measures the variation of sentiment from positive to negative or vice versa. We trained our systems at multiple levels to achieve the maximum cosine similarity of 0.823 and minimum mean square error of 2.170.

Identifying Aspects and Analyzing Their Sentiments from Reviews

The popularity of internet along with the huge number of reviews posted daily via social media, blogs and review sites invokes the research challenges on topic or aspect based analysis. In the recent years, it also has become a challenging task to mine opinions with respect to the aspects from the available unstructured and noisy data. In this paper, we present a novel approach to identify the key terms and its sentiments from the reviews of Restaurants and Laptops with the help of different features and Conditional Random Field based machine learning algorithm. The supervised method achieves F-score of 0.7493380 and 0.6858054 for aspect term identification whereas 0.68982 and 0.6041 of accuracy for aspect based sentiment classification on Restaurant and Laptop reviews, respectively.

Named Entity Recognizer for less resourced language Kokborok

Named Entity Recognition refers to the process of classifying text elements into predefined categories such as person names, organizations, locations, date, quantities etc. In this paper, we described the development of a rule based and a supervised Named Entity Recognizer for the Kokborok language which is less computerized and agglutinative. We used suffix information and Named Entity dictionary for the rule based system, while features like parts-of-speech (POS), context information and suffix etc. were used to develop the supervised system. Margin Infused Relaxed Machine Learning Algorithm is used for developing the supervised system. We achieved the maximum F-score of 83.18% after inclusion of the post-processing technique.

Identifying Temporal Information and Tracking Sentiment in Cancer Patients’ Interviews

Time is an essential component for the analysis of medical data, and the sentiment beneath the temporal information is intrinsically connected with the medical reasoning tasks. The present paper introduces the problem of identifying temporal information as well as tracking of the sentiments/emotions according to the temporal situations from the interviews of cancer patients. A supervised method has been used to identify the medical events using a list of temporal words along with various syntactic and semantic features. We also analyzed the sentiments of the patients with respect to the time-bins with the help of dependency based sentiment analysis techniques and several Sentiment lexicons. We have achieved the maximum accuracy of 75.38% and 65.06% in identifying the temporal and sentiment information, respectively.