Indiana University-Purdue University Indianapolis (IUPUI) / Textual emotion classification is a task in affective AI that branches from sentiment analysis and focuses on identifying emotions expressed in a given text excerpt. It has a wide variety of applications that improve human-computer interactions, particularly to empower computers to understand subjective human language better. Significant research has been done on this task, but very little of that research leverages one of the most emotion-bearing symbols we have used in modern communication: Emojis. In this thesis, we propose several transformer-based models for emotion classification that processes emojis as input tokens and leverages pretrained models and uses them , a model that processes Emojis as textual inputs and leverages DeepMoji to generate affective feature vectors used as reference when aggregating different modalities of text encoding. To evaluate ReferEmo, we experimented on the SemEval 2018 and GoEmotions datasets, two benchmark datasets for emotion classification, and achieved competitive performance compared to state-of-the-art models tested on these datasets. Notably, our model performs better on the underrepresented classes of each dataset.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

Metamemory is “knowing about knowing” (Flavell, 1971) and is theorized as a cognitive process that monitors and controls the memory system (Flavell & Wellman, 1975; Nelson & Narens, 1990). The predominate finding in the metamemory and aging literature is that metamemory is unimpaired by aging, even when memory is impaired by aging (Eakin & Hertzog, 2006; 2012; Connor, Hertzog, & Dunlosky, 1997; Hertzog, Sinclair, & Dunlosky, 2010; Eakin, Hertzog, & Harris, 2014, but see Souchay, Moulin, Clarys, Taconnat, & Isingrini, 2007). However, a study examining metamemory for emotional words suggests older adults may show metamemory impairment when predicting memory for emotional words (Tauber & Dunlosky, 2012). This finding challenges the supposition that metamemory is unimpaired with aging. The purpose of the current study was to expand on the results from Tauber and Dunlosky (2012) to determine whether their findings were due to methodological issues rather than age-related deficits in metamemory.

Early sensation novels such as Wilkie Collins’s The Woman in White, Mary Elizabeth Braddon’s Lady Audley’s Secret, and Ellen Wood’s East Lynne use the eighteenth-century notion of sentiment in very distinct manners. These novels demonstrate a perspective in transition regarding sentimentality in how they apply sentimental qualities to very specific character types. Some characters are extremely sentimental, whereas others appear completely void of emotion and are even described as automata. These sensation novels even feature sentimental journeys and objects, as well as allusions to sentimental novels such as Laurence Sterne’s A Sentimental Journey and Henry Mackenzie’s Man of Feeling. The occurrence of sentimentality in these sensation novels aligns characters into two categories: those that are controlled (and in some instances debilitated) by sentiment, and those that can control their feelings. Thus, the sensation novel calls into question the authenticity of emotional expression as it is represented in the sentimental literary tradition. Existing research on these novels tends to focus on gender and madness, a majority of which focuses specifically on madwomen. Instances of women being driven to madness, however, also coincides with a pattern of sentimental behaviors that male characters share. These overly sentimental characters rarely, if ever, demonstrate rational thinking, and are cast in a negative light. In contrast, the sensation novel casts non-sentimental characters of both genders as skeptics and investigators who generally meet felicitous ends. This thesis will contribute to existing scholarship on sensation fiction by taking into account how these novels treat excessive affect as a sign of generic critique rather than just a biological symptom of a pathologized woman.