Emoji-based semantic representations for abstract and concrete concepts

The Lexicon of Emoji? Conventionality Modulates Processing of Emoji

Emoji have been ubiquitous in communication for over a decade, yet how they derive meaning remains underexplored. Here, we examine an aspect fundamental to linguistic meaning-making: the degree to which emoji have conventional lexicalized meanings and whether that conventionalization affects processing in real-time. Experiment 1 establishes a range of meaning agreement levels across emoji within a population; Experiment 2 measures accuracy and response times to word-emoji pairings in a match/mismatch task. In this experiment, we found that accuracy and response time both correlated significantly with the level of population-wide meaning agreement from Experiment 1, suggesting that lexical access of single emoji may be comparable to that of words, even out of context. This is consistent with theories of a multimodal lexicon that stores links between meaning, structure, and modality in long-term memory. Altogether, these findings suggest that emoji can allow a range of entrenched, lexicalized representations.

The Multidimensional Lexicon of Emojis: A New Tool to Assess the Emotional Content of Emojis

Emerging studies suggest that emojis can make important contributions to the emotional content and meaning of digital messages. Yet researchers currently lack adequate tools to incorporate emojis into their analyses. To address this gap, we used over 3 million Twitter posts from a period of 17 months and emotion ratings provided by 2,230 human raters to develop and validate the Multidimensional Lexicon of Emojis (MLE). This new lexicon consists of 359 common emojis rated on ten emotion and sentiment dimensions. The MLE is an open-access tool that holds promise for those interested in conducting a comprehensive analysis of the emotional content of digital communication that incorporates emojis and goes beyond the dimensions of negativity and positivity.

A multi-modal and multi-scale emotion-enhanced inference model based on fuzzy recognition

Only the label corresponding to the maximum value of the fully connected layer is used as the output category when a neural network performs classification tasks. When the maximum value of the fully connected layer is close to the sub-maximum value, the classification obtained by considering only the maximum value and ignoring the sub-maximum value is not completely accurate. To reduce the noise and improve classification accuracy, combining the principles of fuzzy reasoning, this paper integrates all the output results of the fully connected layer with the emotional tendency of the text based on the dictionary to establish a multi-modal fuzzy recognition emotion enhancement model. The provided model considers the enhancement effect of negative words, degree adverbs, exclamation marks, and question marks based on the smallest subtree on the emotion of emotional words, and defines the global emotional membership function of emojis based on the corpus. Through comparing the results of CNN, LSTM, BiLSTM and GRU on Weibo and Douyin, it is shown that the provided model can effectively improve the text emotion recognition when the neural network output result is not clear, especially for long texts.

Eliciting semantic properties: methods and applications

Asking subjects to list semantic properties for concepts is essential for predicting performance in several linguistic and non-linguistic tasks and for creating carefully controlled stimuli for experiments. The property elicitation task and the ensuing norms are widely used across the field, to investigate the organization of semantic memory and design computational models thereof. The contributions of the current Special Topic discuss several core issues concerning how semantic property norms are constructed and how they may be used for research aiming at understanding cognitive processing.