Constructing Social Intentional Corpora to Predict Click-Through Rate for Search Advertising

Constructing Social Intentional Corpora to Predict Click-Through Rate for Search Advertising Yi-Ting Chen, Hung-Yu Kao Department of Computer Science and Information Engineering National Cheng Kung University P76001221@mail.ncku.edu.tw, hykao@mail.ncku.edu.tw Abstract In the beginning, search engines provide placements next to the original search results for advertisers on specific keywords. Since users often search for their interests or purchasing decision, timely presenting proper advertisements to users will encourage them to click on search ads. With the rapid growth of advertising, there is a bidding mechanism that advertisers need to bid keywords on their ads. They should carefully compose keywords in order to enhance the opportunity for their ads to be clicked. Until now, how to efficiently improve the ad performance to earn more clicks remains a main task. In this paper, we focus on the scope of smart phone and produce a social intentional model with advertising based features to forecast future trend on ads’ click-through rate (CTR). In terms of social intentional model, we analyze Chinese text content of technology forum to derive social intentional factors which are Hotness, Sentiment, Promotion, and Event. Our results indicate that with knowing public opinions or occurring events beforehand can efficiently enhance click prediction. This will be very helpful for advertisers on adjusting bidding keywords to improve ad performance via social intention. Keywords: Advertising, Sponsored Search, Click-Through Rate, Social Intention. 1. Introduction For online search advertising, the well-known search engines such as Bing, Google, and Yahoo! enable ads to be shown on the top banner or alongside the search results. This generates most of the revenue for search engines. The most common mechanism is cost-per-click (CPC), which means the advertiser bid on keywords but only be charged for each user click on the ad. Both search engines and advertisers look forward to enhancing the ad’s click-through rate (CTR), which indicates the probability of the number of ad clicks divided by the number of ad impression. The ad position is on the basis of the ranking score which is computed by the multiplication of CPC and ad quality score. The ad quality depends on plenty of factors that cause an ad to be clicked like ad’s keywords, historical CTR, title, description, display URL, landing page, etc. Moreover, CTR is an important and direct metric Proceedings of the Twenty-Fifth Conference on Computational Linguistics and Speech Processing (ROCLING 2013) 278 for measuring advertised performance. This paper will focus on forecasting ad keyword’s CTR trend, since different bidding keywords in the same ad have various CTR values. Target on the popular 3C products: smart phones, we use the public information from technology forum to predict ups and downs of the next day CTR. As [1] statistics, the top three most important factors influencing consumer choice of mobile phones are: innovative features, recommendation and price. We extend these criteria as following factors: Hotness, Sentiment, Promotion, and Event. All these factors may affect ad’s future CTR as Figure 1 depicted. For example the releasing news, a kind of events, may trigger users …

Content truncated to 500 words