section{Introduction}
Many new forms of communication have emerged in the past few decades such as text messaging and have become quite popular and important. These new forms of communication convey huge range of information and are also popularly used to share sentiments and opinions about different events and topics. We have worked on the following task. The task is:
egin{itemize}
item Given a message, classify whether the message is of positive, negative, or neutral sentiment. For messages conveying both a positive and negative sentiment, whichever is the stronger sentiment should be chosen.
end{itemize}
pagebreak
section{Motivation}
We often encounter many challenges when we work with these informal texts like tweets that when we work with traditional texts like newswire data. Tweets are generally short and crisp: they have to be concluded in a sentence or two. And that makes the use of language very informal, along with a lot of newly created spellings, slang, new abbreviations like tc tor "take care", gr8 for "great" and so on. And along with all this we have the hash tags with perform the task equivalent to tagging for the Twitter messages. Recently, the task of handling such challenges and automatically understand the opinions conveyed by these tweets has become quite popular and has become the subject of research. \
One important aspect of the tweets is that they have highly structured data about different aspect of the actual communication like location, language, individuals, time, etc. Twitter keeps track of different pieces of relevant information in JSON format and we can model such information to our greater use. This associated information is useful for a variety of purposes, including but not ...
... middle of paper ...
...on tweets for training. Our method achieves good accuracy with relatively small data size.
pagebreak
section{Future Work}
egin{itemize}
item We have covered most of the features in our classification. Bit, we didn't include effect of following features on classification accuracy.
egin{itemize}
item Taking care of emotions conveyed by abbreviations
item Analysing if subsequent sentences in a tweet are more important. (For eg. giving greater weight to a $2^{nd}$ line in a tweet of 2 lines.)
end{itemize}
item Although it was clear from work done by others on the same problem that SVM tends to perform better than other classifiers, it would be interesting to see how hybrid of other classifiers (like naive bayes classifier) with SVM would perform. (In our work we tried hybrid of bag of words with SVM which improved the accuracy)
end{itemize}
Kay Arthur teaches how to recognize key words and phrases by creating lists, summarizing chapt...
Jean Carletta, “Assessing agreement on classification tasks: The kappa statistic”. Computational Linguistics, MIT Press Cambridge, MA, USA, Vol. 22, No.2, pp. 249–254, 1996.
This is because the effects of the medium on a personal and social scale as the extension of us can result from a new scale that is introduced into our lives by the extension of ourselves and by any kind of new technology (McLuhan, 1964, p. 7). In this case, the medium could be twitter. Created in March 2006 by Jack Dorsey, Noah Glass, Biz Stone, and Evan Williams, twitter has proven to be the largest source of breaking news and social networking site. Since its beginnings, twitter is the medium
Smith, Aaron and Joanna Brenner. “Twitter Use 2012.” PewResearch Internet Project. 1-3. Web. 15 Mar. 2014.
Social media is a revolution, which we are currently experiencing. It has changed the way people communicate and interact with one another, and opens up many more avenues to share news, information, and just general chit chat. Social media is relatively quiet young, but is here to stay for the foreseeable future. We are now at a point where online, we can share, read and react to lots of individual information being posted on microblogging websites, such as Twitter, Facebook, Google+, Tumblr and more. Twitter in particular has been widely embraced, and will centre most of the discussion.
With the added features in smartphones, word prediction can be difficult because it automatically pulls up a word, which is similar to the word previously used. So, the word prediction will give the same wo...
The data is already being generated as the use of blogs and online reviews increase. Sites like Amazon, the biggest online retailer, make reviews about products and sellers available and searchable for consumers. Aggregating 5 star ratings or binary measures, like recommend and not recommend, is not difficult, even with from thousands of records. However, free-form text comments are more difficult to summarize. Sorting and categorizing these opinions is called sentiment analysis. Companies already spend resources to research customer satisfaction and sentiment analysis is a great research tool for consumers and business.
The Viterbi algorithm analyzes English text. Probabilities are assigned to each word in the context of the sentence. A Hidden Markov Model for English syntax is used in which the probability of the word is dependent on the previous word or words. The probability of word or words followed by a word in the sentence the probability is calculated for bi-gram, tri-gram and 4-gram.Depending on the length of the sentence the probability is calculated for n-grams [1].
Twitter and Instagram are Social Media sites that allow users to communicate with others. Twitter is used to communicate small thoughts. Pe...
We can tell some interesting things from looking at our confusion matrix. For one thing, the model misclassified instances that were NO almost as many times as it correctly classified these instances. On the other hand, our model did a much better job of correctly classifying instances in the YES category.
Lets take a look at how Twitter has changed the gathering, delivery and consumption of news. Looking at tactics of the influence of social media and the people has been known to be called navigating news online. “Facebook news users get more news from friends and family and see it as news they might well have gotten someplace else if Facebook did not exist. For Twitter users, though, the news links come from a more even mix of family and friends and news organizations. Most of these users also feel that without Twitter, they would have missed this kind of news”(Pew Research Center). Instead
Jurafsky, D. & Martin, J. H. (2009), Speech and Language Processing: International Version: an Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, 2nd ed, Pearson Education Inc, Upper Saddle River, New Jersey.
Social media has become a major epidemic in today’s society. According to millions of people have signed up on social media websites, allowing their basic information to be shared with the world wide web. Two of the biggest social media websites today are Facebook and Twitter. The new generation tends to use Twitter over Facebook, the older generation prefer Facebook over Twitter. Though Facebook and Twitter serve the same purpose and have many similarities, they both differ in many ways.
In recent years, technology has become the most used and preferred way of communicating, extending across many platforms. All of these programs, such as e-mail, instant messaging, social networking websites in conjunction with text messaging and the ability to access all of these entities on the go, have come into fruition based on the immense and widely found growth made in technological advancements that have occurred in our society. With this, a massive change has developed in regards to referencing how we as humans engage in communication. We have now shifted into a society that relies heavily on the existence of digital communication, whether it be through the means of a mobile device (text messaging) or the Internet (Facebook, Twitter,
Twitter is also important for more than this social aspect. It also has a practical benefit for business to promote products, theologians to discuss faith, and for scientists to announce their latest discoveries. While these do not appear in the top 20 list, they do play a vital part in th...