Team Accuro Project Overview

HOME

ABOUT US

PROJECT OVERVIEW

PROJECT MANAGEMENT

DOCUMENTATION

Introduction and Project Background

We live today, in what could be best described as the age of consumerism, where, what the consumer increasingly looks for, is information to distinguish between products. With this rising need for expert opinion and recommendations, crowd-sourced review sites have brought forth one of the most disruptive business forces of modern age. Since Yelp was launched in 2005, it has been helping customers stay away from bad decisions while steering towards good experiences via a 5-star rating scale and written text reviews. With its vast database of reviews, ratings and general information, Yelp not only makes decision making for its millions of users much easier but also makes its reviewed businesses more profitable by increasing store visits and site traffic.

The Yelp Dataset Challenge provides data on ratings for several businesses across 4 countries and 10 cities to give students an opportunity to explore and apply analytics techniques to design a model that improves the pace and efficiency of Yelp’s recommendation systems. Using the dataset provided for existing businesses, we aim to identify the main attributes of a business that make it a high performer (highly rated) on Yelp. Since restaurants form a large chunk of the businesses reviewed on Yelp, we decided to build a model specifically to advice new restaurateurs on how to become their customers’ favourite food destination.

With Yelp’s increasing popularity in the United States, businesses are starting to care more and more about their ratings as “an extra half star rating causes restaurants to sell out 19 percentage points more frequently”. This profound effect of Yelp ratings on the success of a business makes our analysis even more crucial and relevant for new restaurant owners. Why do some businesses rank higher than others? Do customers give ratings purely based on food quality, does ambience triumph over service or do geographic locations of businesses affect the rating pattern of customers? Through our project we hope to analyse such questions and thereby be able to advice restaurant owners on what factors to look out for.

Related Work

In the paper Sentiment in Twitter Events (Thelwall et al., 2011), more than 34 million tweets are assessed based on whether popular events are typically associated with increases in sentiment strength. Using the top 30 events, determined by a measure of relative increase in term usage, the results give strong evidence that popular events are normally associated with increases in negative sentiment strength and some evidence that peaks of interest in events have stronger positive sentiment than the time before the peak. It seems that many positive events, such as the Oscars, are capable of generating increased negative sentiment in reaction to them. In our project, we can observe whether main events on the national calendar like National Day and Formula 1 Grand Prix Night Race evoke a positive (e.g. national pride) or negative sentiment (e.g. grievances and inconvenience caused by road closures) among Singaporeans.

The paper Sentiment Analysis of Twitter Audiences: Measuring the Positive or Negative Influence of Popular Twitterers (Bae et al., 2012) analysed over 3 million tweets mentioning, retweeting or replying to the 13 most influential users and investigate whether popular users influence the sentiment changes of their audiences positively or negatively. Results show that most of the popular users such as celebrities have larger positive audiences than negative, while news media such as CNN Breaking News and BBC Breaking News have larger negative audiences. Reason given was that western news agencies mostly report the downside of human nature rather than upbeat and hopeful happenings, whereas social media like Mashable and TechCrunch have audiences that are more positive because they publish useful information and news. In Singapore, the top 20 accounts with the most followers consist of a mix of notable people such as JJ Lin and Lee Hsien Loong and organisations like Straits Times and Singapore Airlines (Chin, 2014). We can see if the same is observed in Singapore, by looking at the specific peaks in the trend graph, if it is caused by a certain influential Twitter user, such as from a news agency, a prominent blogger or celebrity, or a government leader.

Based on retweets of more than 165 000 tweets, the paper Emotions and Information Diffusion in Social Media—Sentiment of Microblogs and Sharing Behavior (Stieglitz et al., 2013) examines whether sentiment occurring in social media content is associated with a user’s information sharing behaviour. Results show that emotionally charged tweets, in particular those containing political content, are more likely to be disseminated compared to neutral ones. In our project, we can examine if political news or messages from news agency and politicians incite cause emotions to run high and create conversation among Twitter users. In A Sentiment Analysis of Singapore Presidential Election 2011 using Twitter Data with Census Correction (Choy et al., 2011), sentiment analysis translate into rather accurate information about the political landscape in Singapore. It predicts correctly the top two contenders in a four-corner fight and that there would be a thin margin between them. This proves that there is value in sentiment analysis in anticipating future events.

A real-time text-based Hedonometer was built to measure happiness of over 63 million Twitter users over 33 months, as recorded in the paper Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter (Dodds et al., 2011). It shows how a highly robust and tunable metric can be constructed with the word list chosen solely by frequency of usage.

Motivation and Project Scope

Being able to identify what make people happy is arguably one of the most important parts of socio-economic development. Increasingly, many public-opinion polls and government agencies have asked citizens the questions related to happiness and wellbeing in their surveys. In the Gallup poll in 2012, Singapore was ranked the most emotionless society and the least positive country in the world. What makes Singaporeans (un)happy? The goal of this project is to apply the use of social media to measure happiness as a less expensive (in terms of time and resources) method to traditional surveys. The motivation behind this project is to be able to visually represent the data that Living Analytics Research Centre (LARC) has collected from Twitter. The data-set provided comprises of social media data in form of tweets published by Singapore-based Twitter users over several months. The key scope to the project would be to create a dashboard that would distinctively represent the Twitter data to us. The Twitter data will consists of information that is provided Twitter, and on top of that, additional predicted user attributes. We will come up with their granular analysis of change in mood trends, periods of significance (may be weekends or any weekday) and other noteworthy actionable insights coming out of analysis done. The dashboard allows users to quickly view and understand what the data is telling them without delving into the data itself. The focus is therefore to create a replicable and scalable dashboard that can accommodate the large amount of data collected by the LARC team.

Work Scope

The system will include the following:

• A timeline based on the tweets provided
• The timeline will display the level of happiness as well as the volume of tweets.
• Each point on the timeline will provide additional information like the overall happiness scores, the level of sentiments for each specific category etc.
• Linked graphical representations based on the time line
• Graphs to represent the aggregated user attributes (gender, age groups etc.)
• Comparison between 2 different user defined time periods
• Optional toggling of volume of tweets with sentiment timeline graph

Work Scope

• Data Collection – Collect Twitter data to be analysed from LARC
• Data Preparation – Clean and transform the data into a readable CSV for upload
• Application Calculations and Filtering – Perform calculations and filters on the data in the app
• Dashboard Construction – Build the application’s dashboard and populate with data
• Dashboard Calibration – Finalize and verify the accuracy of dashboard visualizations
• Stress Testing and Refinement – Test software performance whether it meets the minimum requirements of the clients and * perform any optimizations to meet these.
• Literature Study – Understand sentiment and text analysis in social media
• Software Learning – Learn how to use and integrate various D3.js / Hicharts libraries, and the dictionary word search provided by the client.

Deliverables

• Project Proposal
• Mid-term presentation
• Mid-term report
• Final presentation
• Final report
• Project poster
• A web-based platform hosted on OpenShift.

Introduction and Project Background

Overview

Demographics

Word Association

Methodology

Dashboard

The key aim of this project is to allow the user to be able to explore and analyse the happiness level of the targeted subjects based on a given set of tweets. Tweets are a string of text made up of 140 characters. Tweets may contain shorten URLs, tags (@xyz) or trending topics (#xyz).

The interactive visual model prototype should allow the user to be able to see the past tweets based upon certain significant events and derive a conclusion from the results shown. To be able to do this, we will propose the following methodology. Tweet data will be provided to us from the user via uploading a csv file containing the tweets in the JSON format.

First, we will first display an overview of the tweets that we are looking at. Tweets will be aggregated into intervals based upon the span of tweets’ duration as given in the file upload. Each tweet will have a ‘happiness’ score tagged to it. “Happiness” score is derived from the study at Hedometer.org. Out of the 10,100 words that have a score tagged to it, some of them may not be applicable to words on Twitter. (Please refer to the study to find out how the score is derived). Words that are not applicable will not be used to calculate the score of the tweet and will be considered as a stop/neutral word on the application.

To visualise the words that are mentioned in these tweets, we will use a dynamically generated word cloud. A word cloud is useful in showing the users which are the words that are commonly mentioned in the tweets. The more a particular word is mentioned, the bigger it will appear on the word cloud. Stop/neutral words will be removed to ensure that only relevant words show up on the tag cloud. One thing to note is that the source of the text is from Twitter, which means that depending on the users, these tweets may contain localized words which may be hard to filter out. The list of stop words that we will be using to filter will be based upon this list.

Secondly, there is a list of predicted user attributes that is provided by the client. Each line contains attributes of one user in JSON format. The information is shown below:

• id: refers to twitter id
• gender
• ethnicity
• religion
• age_group
• marital_status
• sleep
• emotions
• topics

This predicted user attributes will be displayed in the 2nd segment where the application allows users to have a quick glance of the demographics of the users.

Third, we will also display the score of the words mentioned based upon the happiness level. This will allow the user to quickly identify the words that are attributing to the negativity or positivity of the set of tweets.

The entire application will entirely be browser based and some of the benefits of doing so include:

• Client does not need to download any software to run the application
• It clean and fast as most of the people who own a computer would probably have a browser installed by default
• It is highly scalable. Work is done on the front-end rather than on the server which may be choked when handling too many requests.

HTML5 and CSS3 will be used primarily for the display. Javascript will be used for the manipulation of the document objects front-end. Some of the open source plugins that we will be using includes:

• Highchart.js – a visualisation plugin to create charts quickly.
• Jquery – a cross-platform JavaScript library designed to simplify the client-side scripting of HTML
• Openshift – Online free server for live deployment
• Moment.js – date manipulation plugin

Machine Learning

Given the limitations of the Happiness index score by Hedonometer, we are attempting to use these sample tweets to learn and generate a more robust set of lexicon/dictionary. Machine learning is a scientific discipline that explores the construction and study of algorithms that can learn from data. Such algorithms operate by building a model from example inputs and using that to make predictions or decisions rather than following a strictly static program. This dictionary will be built on top of the research done by Hedonometer as use their dictionary as a starting point. To calculate the score of a particular tweet, words that appears in a given tweet and in the Hedonometer dictionary are used to calculate the overall happiness score of the entire tweet. To determine whether a tweet is positive , the overall score of the tweet has to be more than 5 (center score in the happiness index) multiplied by the number of words that coincide in the dictionary, and less than that amount to be considered negative. Based on a given set of sample tweets, we track the number of times a particular word appears in a "positive" tweet and the number of times it appears in a "negative" tweet. The percentage in which it appears positive will be how positive it is against other words. On top of that, words that were previously not documented will also be included and their score counted as well.

Lexical Affinity

Another limitation of the Hedometer is that it only considers the score of one word at a time, which can paint a very different picture if we were to look at words association. Take for example, a tweet " I dislike New York" may seem negative to a human observer, but neutral to the machine as the scores of "dislike" and "new" cancels one another out, or in the case of "That dog is pretty ugly", where "pretty" and "ugly" cancels one another out. Thus, we need to associate words together to understand the tweet a little better.

Lexical Affinity assigns arbitrary words a probabilistic affinity for a particular topic or emotion. For example, ‘accident’ might be assigned a 75% probability of indicating a negative event, as in ‘car accident’ or ‘hurt in an accident’. There are a few lexical affinity types that share high co-occurrence frequency of their constituents [1]:

• grammatical constructs (e.g. “due to”)
• semantic relations (e.g. “nurse” and “doctor”)
• compounds (e.g. “New York”)
• idioms and metaphors (e.g. “dead serious)

The way to do this is to first determine or define the support and confidence threshold that we are willing to accept before associating words with one another. As a rule of thumb, we will go ahead with 75%.

The support of a bigram (2 words) is defined as the proportion of all the set of words which contains these 2 words. Essentially, it is to see if these 2 words occur sufficient number of time to consider the pairing significant. The confidence of a rule is defined by the proportion of these 2 words occurring over the number of times tweets containing the former of these words occurs. Each tweet may contain more than 1 pairing. For example, "It's a pleasant and wonderful experience" yields 3 pairings where "[Pleasant,wonderful][pleasant,experience][wonderful,experience]" can be grouped. Once we have determine the support and confidence level of each of these pairings, we will be able to generate a new dictionary containing these pairings to be run onto new data.

Testing our New Dictionary

To determine the accuracy of the dictionary, human test subjects will be employed to judge whether or not the dictionary is in fact effective in determining the polarity of the tweet. Each human subject will be given 2 tweets to judge, with each of these tweets having a pre-defined score after running through the new dictionary. If the human subject's perception of the 2 tweets coincides with that of the dictionary, the test will be given a positive, else a negative is awarded. A random sample of 100 users will be chosen to do at least 10 comparisons each. At the end of these tests, we will calculate the number of positives over the total tests done. The proportion will determine the accuracy of our dictionary.

Limitations & Assumptions

What Hedonometer Cannot Detect

Negation Handling

Abbreviations, Smileys/Emoticons & Special Symbols

Local Languages & Slangs (Singlish)

Ambiguity

Sarcasm

Project Overall

Limitations	Assumptions
Insufficient predicted information on the users (location, age etc.)	Data given by LARC is sufficiently accurate for the user
Fake Twitter users	LARC will determine whether or not the users are real or not
Ambiguity of the emotions	Emotions given by the dictionary (as instructed by LARC) is conclusive for the Tweets that is provided
Dictionary words limited to the ones instructed by LARC	A comprehensive study has been done to come up with the dictionary

ROI Analysis

As part of LARC’s initiative to study the well-being of Singaporeans, this dashboard will be used as springboard to visually represent Singaporeans on the Twitter space and identify the general sentiments of twitter users based on a given time period. This may provide one of the useful information about people's subjective well-being which helps realise the visions of the smart nation initiative by the Singapore government to understand the well-being of Singaporeans. This project may be a standalone or a series of projects done by LARC.

Future Work

• Scalable larger sets of data without hindering on time and performance
• Able to accommodate real-time data to provide instantaneous analytics on-the-go

References