Sentiment analysis is used as a proxy to measure human emotion, where the objective is to categorize text according to some predefined notion of sentiment. Sentiment analysis datasets are typically constructed with gold-standard sentiment labels, assigned based on the results of manual annotations. When working with such annotations, it is common for dataset constructors to discard "noisy" or "controversial" data where there is significant disagreement on the proper label. In datasets constructed for the purpose of Twitter sentiment analysis (TSA), these controversial examples can compose over 30% of the originally annotated data. We argue that the removal of such data is a problematic trend because, when performing real-time sentiment classification of short-text, an automated system cannot know a priori which samples would fall into this category of disputed sentiment. We therefore propose the notion of a "complicated" class of sentiment to categorize such text, and argue that its inclusion in the short-text sentiment analysis framework will improve the quality of automated sentiment analysis systems as they are implemented in real-world settings. We motivate this argument by building and analyzing a new publicly available TSA dataset of over 7,000 tweets annotated with 5x coverage, named MTSA. Our analysis of classifier performance over our dataset offers insights into sentiment analysis dataset and model design, how current techniques would perform in the real world, and how researchers should handle difficult data.

We investigate how automated, data-driven, personalized feedback in a large-scale intelligent tutoring system (ITS) improves student learning outcomes. We propose a machine learning approach to generate personalized feedback, which takes individual needs of students into account. We utilize state-of-the-art machine learning and natural language processing techniques to provide the students with personalized hints, Wikipedia-based explanations, and mathematical hints. Our model is used in Korbit, 5 a largescale dialogue-based ITS with thousands of students launched in 2019, and we demonstrate that the personalized feedback leads to considerable improvement in student learning outcomes and in the subjective evaluation of the feedback.

Intelligent tutoring systems (ITS) have been shown to be highly effective at promoting learning as compared to other computer-based instructional approaches. However, many ITS rely heavily on expert design and hand-crafted rules. This makes them difficult to build and transfer across domains and limits their potential efficacy. In this paper, we investigate how feedback in a large-scale ITS can be automatically generated in a data-driven way, and more specifically how personalization of feedback can lead to improvements in student performance outcomes. First, in this paper we propose a machine learning approach to generate personalized feedback in an automated way, which takes individual needs of students into account, while alleviating the need of expert intervention and design of hand-crafted rules. We leverage state-of-the-art machine learning and natural language processing techniques to provide students with personalized feedback using hints and Wikipedia-based explanations. Second, we demonstrate that personalized feedback leads to improved success rates at solving exercises in practice: our personalized feedback model is used in , a large-scale dialogue-based ITS with around 20,000 students launched in 2019. We present the results of experiments with students and show that the automated, data-driven, personalized feedback leads to a significant overall improvement of 22.95% in student performance outcomes and substantial improvements in the subjective evaluation of the feedback.

This paper investigates personalization in the field of intelligent tutoring systems (ITS). We hypothesize that personalization in the way questions are asked improves student learning outcomes. Previous work on dialogue-based ITS personalization has yet to address question phrasing. We show that generating versions of the questions suitable for students at different levels of subject proficiency improves student learning gains, using variants written by a domain expert and an experimental A/B test. This insight demonstrates that the linguistic realization of questions in an ITS affects the learning outcomes for students.

In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA) from source to target domain. While self-training generates synthetic training data where natural inputs are aligned with noisy outputs, back-training results in natural outputs aligned with noisy inputs. This significantly reduces the gap between the target domain and synthetic data distribution, and reduces model overfitting to the source domain. We run UDA experiments on question generation and passage retrieval from the Natural Questions domain to machine learning and biomedical domains. We find that back-training vastly outperforms selftraining by a mean improvement of 7.8 BLEU-4 points on generation, and 17.6% top-20 retrieval accuracy across both domains. We further propose consistency filters to remove low-quality synthetic data before training. We also release a new domain-adaptation dataset-MLQuestions containing 35K unaligned questions, 50K unaligned passages, and 3K aligned question-passage pairs.