Filtering by
- Creators: Barrett, The Honors College
One of the key features for social media is social, where social media users actively interact to each via generating content and expressing the opinions, such as post and comment in Facebook. As a result, sentiment analysis, which refers a computational model to identify, extract or characterize subjective information expressed in a given piece of text, has successfully employs user signals and brings many real world applications in different domains such as e-commerce, politics, marketing, etc. The goal of sentiment analysis is to classify a user’s attitude towards various topics into positive, negative or neutral categories based on textual data in social media. However, recently, there is an increasing number of people start to use photos to express their daily life on social media platforms like Flickr and Instagram. Therefore, analyzing the sentiment from visual data is poise to have great improvement for user understanding.
In this dissertation, I study the problem of understanding human sentiments from large scale collection of social images based on both image features and contextual social network features. We show that neither
visual features nor the textual features are by themselves sufficient for accurate sentiment prediction. Therefore, we provide a way of using both of them, and formulate sentiment prediction problem in two scenarios: supervised and unsupervised. We first show that the proposed framework has flexibility to incorporate multiple modalities of information and has the capability to learn from heterogeneous features jointly with sufficient training data. Secondly, we observe that negative sentiment may related to human mental health issues. Based on this observation, we aim to understand the negative social media posts, especially the post related to depression e.g., self-harm content. Our analysis, the first of its kind, reveals a number of important findings. Thirdly, we extend the proposed sentiment prediction task to a general multi-label visual recognition task to demonstrate the methodology flexibility behind our sentiment analysis model.
Sentiment analysis, which is a notably method in text mining, can be used to extract the sentiment from people’s opinion. It then provides us with valuable perception on a topic from the public’s attitude, which create more opportunities for deeper analysis and prediction.
The thesis aims to investigate public’s sentiment towards Bitcoin through analyzing 10 million Bitcoin related tweets and assigning sentiment points on tweets, then using sentiment fluctuation as a factor to predict future crypto fluctuation. Price prediction is achieved by using a machine learning model called Recurrent Neural Network which automatically learns the pattern and generate following results with memory. The analysis revels slight connection between sentiment and crypto currency and the Neural Network model showed a strong connection between sentiment score and future price prediction.
As online media, including social media platforms, become the primary and go-to resource for traditional communication, news and the spread of information is more present and accessible to consumers than ever before. This research focuses on analyzing Twitter data on the ongoing Russian-Ukrainian War to understand the significance of social media during this period in comparison to previous conflicts. The significance of social media and political conflict will be examined through Twitter user analysis and sentiment analysis. This case study will conduct sentiment analysis on a random sample of tweets from a given dataset, followed by user analysis and classification methods. The data will explore the implications for understanding public opinion on the conflict, the strengths and limitations of Twitter as a data source, and the next steps for future research. Highlighting the implications of the research findings will allow consumers and political stakeholders to make more informed decisions in the future.
This project aims to incorporate the aspect of sentiment analysis into traditional stock analysis to enhance stock rating predictions by applying a reliance on the opinion of various stocks from the Internet. Headlines from eight major news publications and conversations from Yahoo! Finance’s “Conversations” feature were parsed through the Valence Aware Dictionary for Sentiment Reasoning (VADER) natural language processing package to determine numerical polarities which represented positivity or negativity for a given stock ticker. These generated polarities were paired with stock metrics typically observed by stock analysts as the feature set for a Logistic Regression machine learning model. The model was trained on roughly 1500 major stocks to determine a binary classification between a “Buy” or “Not Buy” rating for each stock, and the results of the model were inserted into the back-end of the Agora Web UI which emulates search engine behavior specifically for stocks found in NYSE and NASDAQ. The model reported an accuracy of 82.5% and for most major stocks, the model’s prediction correlated with stock analysts’ ratings. Given the volatility of the stock market and the propensity for hive-mind behavior in online forums, the performance of the Logistic Regression model would benefit from incorporating historical stock data and more sources of opinion to balance any subjectivity in the model.
This project aims to incorporate the aspect of sentiment analysis into traditional stock analysis to enhance stock rating predictions by applying a reliance on the opinion of various stocks from the Internet. Headlines from eight major news publications and conversations from Yahoo! Finance’s “Conversations” feature were parsed through the Valence Aware Dictionary for Sentiment Reasoning (VADER) natural language processing package to determine numerical polarities which represented positivity or negativity for a given stock ticker. These generated polarities were paired with stock metrics typically observed by stock analysts as the feature set for a Logistic Regression machine learning model. The model was trained on roughly 1500 major stocks to determine a binary classification between a “Buy” or “Not Buy” rating for each stock, and the results of the model were inserted into the back-end of the Agora Web UI which emulates search engine behavior specifically for stocks found in NYSE and NASDAQ. The model reported an accuracy of 82.5% and for most major stocks, the model’s prediction correlated with stock analysts’ ratings. Given the volatility of the stock market and the propensity for hive-mind behavior in online forums, the performance of the Logistic Regression model would benefit from incorporating historical stock data and more sources of opinion to balance any subjectivity in the model.
As I researched and conducted initial analysis for this project, I quickly ran into a few roadblocks that lead to me needing to pivot off of certain ideas and adapt my initial plans to fit what was actually being done in the current marketing environment. In reality, most businesses are not up for taking the risk of explicitly giving real metrics of their products and services to customers. Due to this, my thesis evolved into finding other ways that companies would use logical appeals to represent their products and comparatively analyze how these companies choose to represent themselves on a social media platform.