We study the effect on click-through rates of applying textual and stylistic features often related to clickbait to headlines of newspaper articles which can be bought in a digital environment. Having a dataset consisting of triples-original headline, rewritten headline, CTR, where CTR is the click-through rate of the rewritten headline in a newsletter from the online kiosk Blendlewe can directly measure whether these "clickbait features" do what they are believed to do: entice readers to click on them. The main findings are as follows. First, the data shows that editors of Blendle indeed often use clickbait features when rewriting headlines. Second, most, but not all, of the clickbait features lead to a statistically significant increase in the number of clicks. Third, predicting the effectiveness of a headline only on the basis of its clickbait features is not possible. The data on which this article is based is publicly available online.

We summarize the findings from Hofmann et al. [6]. Online learning to rank for information retrieval (IR) holds promise for allowing the development of "self-learning" search engines that can automatically adjust to their users. With the large amount of e.g., click data that can be collected in web search settings, such techniques could enable highly scalable ranking optimization. However, feedback obtained from user interactions is noisy, and developing approaches that can learn from this feedback quickly and reliably is a major challenge. In this paper we investigate whether and how previously collected (historical) interaction data can be used to speed up learning in online learning to rank for IR. We devise the first two methods that can utilize historical data (1) to make feedback available during learning more reliable and (2) to preselect candidate ranking functions to be evaluated in interactions with users of the retrieval system. We evaluate both approaches on 9 learning to rank data sets and find that historical data can speed up learning, leading to substantially and significantly higher online performance. In particular, our preselection method proves highly effective at compensating for noise in user feedback. Our results show that historical data can be used to make online learning to rank for IR much more effective than previously possible, especially when feedback is noisy.

Modern search systems are based on dozens or even hundreds of ranking features. The dueling bandit gradient descent (DBGD) algorithm has been shown to effectively learn combinations of these features solely from user interactions. DBGD explores the search space by comparing a possibly improved ranker to the current production ranker. To this end, it uses interleaved comparison methods, which can infer with high sensitivity a preference between two rankings based only on interaction data. A limiting factor is that it can compare only to a single exploratory ranker.We propose an online learning to rank algorithm called multileave gradient descent (MGD) that extends DBGD to learn from so-called multileaved comparison methods that can compare a set of rankings instead of merely a pair. We show experimentally that MGD allows for better selection of candidates than DBGD without the need for more comparisons involving users. An important implication of our results is that orders of magnitude less user interaction data is required to find good rankers when multileaved comparisons are used within online learning to rank. Hence, fewer users need to be exposed to possibly inferior rankers and our method allows search engines to adapt more quickly to changes in user preferences.

Evaluation methods for information retrieval systems come in three types: offline evaluation, using static data sets annotated for relevance by human judges; user studies, usually conducted in a labbased setting; and online evaluation, using implicit signals such as clicks from actual users. For the latter, preferences between rankers are typically inferred from implicit signals via interleaved comparison methods, which combine a pair of rankings and display the result to the user. We propose a new approach to online evaluation called multileaved comparisons that is useful in the prevalent case where designers are interested in the relative performance of more than two rankers. Rather than combining only a pair of rankings, multileaved comparisons combine an arbitrary number of rankings. The resulting user clicks then give feedback about how all these rankings compare to each other. We propose two specific multileaved comparison methods. The first, called team draft multileave, is an extension of team draft interleave. The second, called optimized multileave, is an extension of optimized interleave and is designed to handle cases where a large number of rankers must be multileaved. We present experimental results that demonstrate that both team draft multileave and optimized multileave can accurately determine all pairwise preferences among a set of rankers using far less data than the interleaving methods that they extend.