Refine
Document Type
- Article (1)
- Conference Proceeding (1)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Keywords
- Evaluation (2) (remove)
Academic search systems aid users in finding information covering specific topics of scientific interest and have evolved from early catalog-based library systems to modern web-scale systems. However, evaluating the performance of the underlying retrieval approaches remains a challenge. An increasing amount of requirements for producing accurate retrieval results have to be considered, e.g., close integration of the system’s users. Due to these requirements, small to mid-size academic search systems cannot evaluate their retrieval system in-house. Evaluation infrastructures for shared tasks alleviate this situation. They allow researchers to experiment with retrieval approaches in specific search and recommendation scenarios without building their own infrastructure. In this paper, we elaborate on the benefits and shortcomings of four state-of-the-art evaluation infrastructures on search and recommendation tasks concerning the following requirements: support for online and offline evaluations, domain specificity of shared tasks, and reproducibility of experiments and results. In addition, we introduce an evaluation infrastructure concept design aiming at reducing the shortcomings in shared tasks for search and recommender systems.
Online services such as social networks, online shops, and search engines deliver different content to users depending on their location, browsing history, or client device. Since these services have a major influence on opinion forming, understanding their behavior from a social science perspective is of greatest importance. In addition, technical aspects of services such as security or privacy are becoming more and more relevant for users, providers, and researchers. Due to the lack of essential data sets, automatic black box testing of online services is currently the only way for researchers to investigate these services in a methodical and reproducible manner. However, automatic black box testing of online services is difficult since many of them try to detect and block automated requests to prevent bots from accessing them.
In this paper, we introduce a testing tool that allows researchers to create and automatically run experiments for exploratory studies of online services. The testing tool performs programmed user interactions in such a manner that it can hardly be distinguished from a human user. To evaluate our tool, we conducted - among other things - a large-scale research study on Risk-based Authentication (RBA), which required human-like behavior from the client. We were able to circumvent the bot detection of the investigated online services with the experiments. As this demonstrates the potential of the presented testing tool, it remains to the responsibility of its users to balance the conflicting interests between researchers and service providers as well as to check whether their research programs remain undetected.