CENNLP at SemEval-2018 Task 1: Constrained Vector Space Model in Affects in Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 329–333 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics CENNLP at SemEval-2018 Task 1: Constrained Vector Space Model in Affects in Tweets Naveen J R, Barathi Ganesh H. B., Anand Kumar M, Soman K P Center for Computational Engineering and Networking (CEN) Amrita School of Engineering, Coimbatore Amrita Vishwa Vidyapeetham, India cb.en.p2cen16011@cb.students.amrita.edu, barathiganesh.hb@gmail.com, m anandkumar@cb.amrita.edu Abstract This paper discusses on task 1, ”Affect in Tweets” sharedtask, conducted in SemEval- 2018. This task comprises of various sub- tasks, which required participants to analyse over different emotions and sentiments based on the provided tweet data and also measure the intensity of these emotions for subsequent subtasks. Our approach is to come up with a model for all the subtasks on count based representation and use machine learning tech- niques for regression and classification related tasks. In this work, we use bag of words tech- nique for supervised text classification and re- gression. . Further, fine tuning on various pa- rameters for the bag of word, representation model we acquired better scores over various other baseline models (Vinayan et al.) partici- pated in the sharedtask. 1 Introduction A huge portion of analysis in natural language pro- cessing try to find better understand and process various kinds of info in text. Day by day the devel- opment of social websites, blogging and the con- summation of technologies gives vast amount text data on the internet, which opened a space to study peoples feeling, reviews, and emotion from their own written languages, called sentimental analy- sis. Sentimental analysis has so many attractions and has done so many research (Zhu et al., 2014) in this area. Sentiment analysis remains a sequence of tech- niques, approaches, and tools about sensing and mining subjective info (such as opinion and at- titudes) from language (Bravo-Marquez et al., 2014). Traditional approaches (Kiritchenko et al., 2014; Mohammad et al., 2013) are finding out the polarity of the positive, negative, neutral classification problem (Mohammad, 2018; Bravo- Marquez et al., 2015). Recent research in sen- timental analysis (Mohammad and Kiritchenko, 2018) are done on the data-driven algorithm view point. But at the same time combination of good linguistic awareness data can increase the perfor- mance and insights about the task. We used ma- chine learning techniques to build the model. Lin- ear regression, random forest methods are used re- spectively for prediction and classification tasks. A mathematical system or an algorithm need some form of numeric representation to work with. The naive way of representing a word in vector form is one hot representation but it is a very ineffec- tive way for representing a large corpus. In a more effective way, we need some semantic sim- ilarities (Soman et al., 2016) to nearby points, thus creating the representation bring beneficial info about the word actual meaning, called word embedding models that are categorized based on count and predictive word embedding models. Both embedding models at least some way …

Content truncated to 500 words