When complexity becomes interesting

Abstract

How to provide users a positive experience during interaction with information (i.e., the "Information eXperience" (IX)) is still an open question. As a starting point, this work investigates how the emotion of interest can be influenced by modifying the complexity of the information presented to users. The appraisal theory of interest suggests a "sweet spot" where interest will be at its peak: information that is novel and complex yet still comprehensible. This "sweet spot" is approximated using two studies. Study One develops a computational model of textual complexity founded on psycholinguistic theory on processing difficulty. The model was trained and tested on 12,420 articles, achieving a classification performance of 90.87% on two classes of com- plexity. Study Two puts the model to its ultimate test: Its application to change the user's IX. Using 18 news articles the influence of complexity on interest and its appraisals is unveiled. A structural equation model shows a positive influence of complexity on interest, yet a negative influence of comprehensibility, confirming a seemingly paradoxical relationship between complexity and interest. By showing when complexity becomes interesting, this paper shows how information systemscan use the model of textual complexity to construct an interesting IX.

Recall oriented search on the web using semantic annotations

“…When too many irrelevant results are found, the data will become too noisy to drive conclusions from and, consequently, the user's motivation to go through the search results will decline. Additionally to the match of the search words, other criteria for relevance can be considered [10].…”

Explaining Student Behavior at Scale

“…This argument is similar to that of [28], who argues that it is difficult to unambiguously assign meaning to surface-level indicators such as a certain number of words per sentence. Notable exceptions are in [34,33], who apply deep syntactic-semantic analyses to better reflect the complex cognitive processes during reading.…”

“…To define a plausible and robust measure of complexity, we adopt a set of features introduced by [33]. Each of these features are based on well-known psycholinguistic findings on the causes of reading difficulty and are designed to be robust against overfitting.…”

“…The applicability and robustness of this model has been shown elsewhere. The model used in [33] predicted human ratings of complexity with r = .442 on a new data set not used during model training. We will describe each of the features shortly.…”

“…Likewise, for the interest in text, [31] show that interested readers have a lower reading time than non-interested readers. In turn, this can also be explained by textual complexity, such that complexity increases interest up to the point that it becomes too difficult to understand and slows down reading [33,14]. Similarly, a lack of complexity reduces interest, causing readers to be more easily distracted while reading [31].…”