Computer Sciences Commons^™

Tweets R Us: Predicting Personality From Language And Emoji Use On Twitter, Maxwell Meckling, Sarah Shoup, D. E. Chan-Tin, Shelia Kennison

Computer Science: Faculty Publications and Other Works

The research investigated the suggestion from prior research that language and emojis use on Twitter and other social media platforms can predict users’ personality and gender (Adali et al., 2014; Golbeck et al., 2011; Li et al., 2019; Moreno et al., 2019; Raess, 2018). Some studies have also analyzed Twitter language to identify individuals with specific health conditions (e.g., alcohol recovery, Golbeck, 2012; sleep problems, Suarez et al., 2018).

If strategies to predict Twitter users’ characteristics prove to be successful, future efforts to direct persuasive messages related to recommended practices in public health and/or cybersecurity will be possible. Commercial applications …

Somewhere Over The Rainbow: Exploring The Sense For Relevance In Children, Monica Landoni, Theo Huibers, Emiliana Murgia, Mohammad Aliannejadi, Maria Soledad Pera

Computer Science Faculty Publications and Presentations

We explore the facets of relevance that guide children when assessing materials retrieved by search engines when looking for information in the classroom. We involved children in a collaborative exercise and asked them to design innovative icons to point their peers towards useful results. We also asked them to complete a survey meant to capture explicit motivators guiding their design. This resulted in a rich set of metaphors. Analysis of the emerging metaphors is what allowed us to identify and discuss the many interpretations of relevance children naturally assign to resources they find in response to school-related information discovery …

Effect Of Text Processing Steps On Twitter Sentiment Classification Using Word Embedding, Manar D. Samad, Nalin D. Khounviengxay, Megan A. Witherow

Computer Science Faculty Research

Processing of raw text is the crucial first step in text classification and sentiment analysis. However, text processing steps are often performed using off-the-shelf routines and pre-built word dictionaries without optimizing for domain, application, and context. This paper investigates the effect of seven text processing scenarios on a particular text domain (Twitter) and application (sentiment classification). Skip gram-based word embeddings are developed to include Twitter colloquial words, emojis, and hashtag keywords that are often removed for being unavailable in conventional literature corpora. Our experiments reveal negative effects on sentiment classification of two common text processing steps: 1) stop word removal …

A Framework To Understand Emoji Meaning: Similarity And Sense Disambiguation Of Emoji Using Emojinet, Sanjaya Wijeratne

Browse all Theses and Dissertations

Pictographs, commonly referred to as `emoji’, have become a popular way to enhance electronic communications. They are an important component of the language used in social media. With their introduction in the late 1990’s, emoji have been widely used to enhance the sentiment, emotion, and sarcasm expressed in social media messages. They are equally popular across many social media sites including Facebook, Instagram, and Twitter. In 2015, Instagram reported that nearly half of the photo comments posted on Instagram contain emoji, and in the same year, Twitter reported that the `face with tears of joy’ emoji has been tweeted 6.6 …