Improving Website Hyperlink Structure Using Server Logs

Abstract

Good websites should be easy to navigate via hyperlinks, yet maintaining a high-quality link structure is difficult. Identifying pairs of pages that should be linked may be hard for human editors, especially if the site is large and changes frequently. Further, given a set of useful link candidates, the task of incorporating them into the site can be expensive, since it typically involves humans editing pages. In the light of these challenges, it is desirable to develop data-driven methods for automating the link placement task. Here we develop an approach for automatically finding useful hyperlinks to add to a website. We show that passively collected server logs, beyond telling us which existing links are useful, also contain implicit signals indicating which nonexistent links would be useful if they were to be introduced. We leverage these signals to model the future usefulness of yet nonexistent links. Based on our model, we define the problem of link placement under budget constraints and propose an efficient algorithm for solving it. We demonstrate the effectiveness of our approach by evaluating it on Wikipedia, a large website for which we have access to both server logs (used for finding useful new links) and the complete revision history (containing a ground truth of new links). As our method is based exclusively on standard server logs, it may also be applied to any other website, as we show with the example of the biomedical research site Simtk.

A wikification prediction model based on the combination of latent, dyadic and monadic features

“…The aforementioned studies assume that the manual quality assessment of Wikipedia articles and the associated reviewing processes lead to reliable ground truth about content quality. This idea has been challenged because missing links can exist for a long time (Sunercan & Birturk, 2010), links can be biased towards popularity and importance (Hanada, Cristo, & Pimentel, 2013), and links are rarely clicked (Paranjape, West, Zia, & Leskovec, 2016). This last issue is remarkable as it would be expected that appropriate links should be followed once they are created.…”

“…This last issue is remarkable as it would be expected that appropriate links should be followed once they are created. However, Paranjape et al (2016) showed that 66% of the links are never clicked and that approximately 1% reach around 100 clicks. This may indicate flaws in the reviewing processes.…”

“…Although both underlinking and overlinking should be avoided, overlinked articles make it difficult for users to identify links that likely to aid their understanding. This is a common problem in Wikipedia, according to a study of log data conducted by Paranjape et al (2016). The authors found that most of the links placed by editors are never or rarely clicked.…”

“…A possible reason for the finding by Paranjape et al (2016) is that linking guidelines are not satisfactorily followed by Wikipedia editors. This is not surprising if we note that such guidelines are really reinforced for few articles.…”

“…Finally, the similar results obtained with high quality training (FA, AC or GA) and medium quality training (BC or CC) suggests that either (a) the casual editor and the expert reviewer have a similar understanding about what should be a proper link, or (b) a proper linking style is not determinant on the distinction of medium and high quality classes, or (c) linking is so subjective that it is hard to assess its quality once some basic criteria are met (for instance, no excessive redundancy, exclusion of common elements such everyday words, dates, major geographic features, etc.). Overall, the apparent little use of links in Wikipedia identified by Paranjape et al (2016) indicates that more research is necessary regarding this issue.…”