The inherent nature of social media content poses serious challenges to practical applications of sentiment analysis. We present VADER, a simple rule-based model for general sentiment analysis, and compare its effectiveness to eleven typical state-of-practice benchmarks including LIWC, ANEW, the General Inquirer, SentiWordNet, and machine learning oriented techniques relying on Naive Bayes, Maximum Entropy, and Support Vector Machine (SVM) algorithms. Using a combination of qualitative and quantitative methods, we first construct and empirically validate a gold-standard list of lexical features (along with their associated sentiment intensity measures) which are specifically attuned to sentiment in microblog-like contexts. We then combine these lexical features with consideration for five general rules that embody grammatical and syntactical conventions for expressing and emphasizing sentiment intensity. Interestingly, using our parsimonious rule-based model to assess the sentiment of tweets, we find that VADER outperforms individual human raters (F1 Classification Accuracy = 0.96 and 0.84, respectively), and generalizes more favorably across contexts than any of our benchmarks.

No abstract

Follower count is important to Twitter users: it can indicate popularity and prestige. Yet, holistically, little is understood about what factors -like social behavior, message content, and network structure -lead to more followers. Such information could help technologists design and build tools that help users grow their audiences. In this paper, we study 507 Twitter users and a half-million of their tweets over 15 months. Marrying a longitudinal approach with a negative binomial auto-regression model, we find that variables for message content, social behavior, and network structure should be given equal consideration when predicting link formations on Twitter. To our knowledge, this is the first longitudinal study of follow predictors, and the first to show that the relative contributions of social behavior and message content are just as impactful as factors related to social network structure for predicting growth of online social networks. We conclude with practical and theoretical implications for designing social media technologies.

In the past half-decade, Amazon Mechanical Turk has radically changed the way many scholars do research. The availability of a massive, distributed, anonymous crowd of individuals willing to perform general human-intelligence micro-tasks for micro-payments is a valuable resource for researchers and practitioners. This paper addresses the challenges of obtaining quality annotations for subjective judgment oriented tasks of varying difficulty. We design and conduct a large, controlled experiment (N=68,000) to measure the efficacy of selected strategies for obtaining high quality data annotations from non-experts. Our results point to the advantages of person-oriented strategies over process-oriented strategies. Specifically, we find that screening workers for requisite cognitive aptitudes and providing training in qualitative coding techniques is quite effective, significantly outperforming control and baseline conditions. Interestingly, such strategies can improve coder annotation accuracy above and beyond common benchmark strategies such as Bayesian Truth Serum (BTS).

Little is known about the long-term impact of surviving childhood cancer. Most children diagnosed with cancer now survive into adulthood due to advances in medical treatment. Although the number of survivors of childhood cancer has increased, a review of the literature revealed a paucity of studies that explores survivorship of childhood cancer from the perspective of the adult survivor. The purpose of this phenomenological study was to examine the lived experience of 12 adults who survived childhood cancer. This research methodology allows the meaning or essences of experiences that occurred to be uncovered. Four themes emerged from these data: (1) ongoing consequences for having had cancer, (2) living with uncertainty, (3) the cancer experience is embodied into one's present sense of self, and (4) support is valued. The results of this study demonstrate that a childhood cancer experience affects the life of each survivor, which results in specific health care needs. This knowledge is important as the number of survivors increases. Knowledge of their concerns is imperative prior to providing appropriate health care.