Enhancing keyphrase extraction from microblogs using human reading time

Abstract

The premise of manual keyphrase annotation is to read the corresponding content of an annotated object. Intuitively, when we read, more important words will occupy a longer reading time. Hence, by leveraging human reading time, we can find the salient words in the corresponding content. However, previous studies on keyphrase extraction ignore human reading features. In this article, we aim to leverage human reading time to extract keyphrases from microblog posts. There are two main tasks in this study. One is to determine how to measure the time spent by a human on reading a word. We use eye fixation durations (FDs) extracted from an open source eye‐tracking corpus. Moreover, we propose strategies to make eye FD more effective on keyphrase extraction. The other task is to determine how to integrate human reading time into keyphrase extraction models. We propose two novel neural network models. The first is a model in which the human reading time is used as the ground truth of the attention mechanism. In the second model, we use human reading time as the external feature. Quantitative and qualitative experiments show that our proposed models yield better performance than the baseline models on two microblog datasets.

Roles and Research Trends of Neuroscience on Major Information Systems Journal: A Bibliometric and Content Analysis

“…In the mixed study, Schultheiss and Lewandowski (2021) adopted a mixed-research method, including pre-study interviews, an eye-tracking experiment, and a post-experiment questionnaire, to explore the effects of knowledge level and device screen size on users’ ability to distinguish between search results and advertisements when using search engines. Zhang and Zhang (2021) first used eye-tracking to obtain the time spent on reading words and subsequently used a neural network model to integrate the time spent on reading words into keyphrase extraction models. Ellison et al (2020) adopted eye-tracking, survey, and interview methods to confirm that there was no difference in viewing duration between clicking in and not clicking on Facebook content.…”

“…It can be found that the use of neuroscience tools is gradually diversified. In particular, mixed research methods will gradually become popular in 2020 ( Ellison et al, 2020 ; Zhang and Zhang, 2021 ). Whether it is empirical research combined with neuroscience experiments, traditional experiments combined with neuroscience experiments, or the integration of multiple neuroscientific experimental tools, it can be found that mixed research is relatively new in NeuroIS.…”

Does attention mechanism possess the feature of human reading? A perspective of sentiment classification task

“…In recent years, eye-tracking values, including total fixation time, fixation times, and first fixation time, have been used for part-of-speech tagging (Barrett et al, 2016), syntactic analysis (Agrawal and Rosa, 2020), sentence classification (Barrett et al, 2018;Long et al, 2017), information extraction (Barrett and Hollenstein, 2020;Hollenstein and Zhang, 2019;Zhang and Zhang, 2021) , and text understanding (Malmaud et al, 2020;Zheng et al, 2019), which has been proved to improve the performance of deep learning models. Besides, eye-tracking values are also widely used in behavioral sciences to analyze users' behaviors, such as searching and querying information (Gwizdka et al, 2019;Sachse, 2019;Wu and Huang, 2018).…”

“…It uses eye-trackers to capture the time or fixation times of eye gaze on each word (Rayner et al, 2012). ETCs have been applied to various NLP tasks, e.g., part-ofspeech tagging (Barrett et al, 2016), sentiment analysis (Mishra, Kanojia, Nagar, et al, 2016), multiword expression (Rohanian et al, 2017), keyphrase extraction (Zhang and Zhang, 2021), etc. These studies used eye-tracking values to optimize the attention mechanism, but they lack to explain the rationality of this approach.…”

“…, 2016b), multiword expression (Rohanian et al. , 2017), keyphrase extraction (Zhang and Zhang, 2021), etc. These studies used eye-tracking values to optimize the attention mechanism, but they lack to explain the rationality of this approach.…”