Impact of query intent and search context on clickthrough behavior in sponsored search

Implicit feedback techniques may be used for query intent detection, taking advantage of user behavior to understand their interests and preferences. In sponsored search, a primary concern is the user’s interest in purchasing or utilizing a commercial service, or what is called online commercial intent. In this paper, we develop a methodology for employing the content of search engine result pages (SERPs), along with the information obtained from query strings, to study characteristics of query intent, with a particular focus on sponsored search. Our work represents a step toward the development and evaluation of an ontology for commercial search, considering queries that reference specific products, brands, and retailers. Characteristics of query categories are studied with respect to aggregated user clickthrough behavior on advertising links. We present a model for clickthrough behavior that considers the influence of such factors as the location of ads and the rank of ads, along with query category. We evaluate our work using a large corpus of clickthrough data obtained from a major commercial search engine. In addition, the impact of query intent is studied on clickthrough rate, where a baseline model and the query intent model are compared for the purpose of calculating an expected ad clickthrough rate. Our findings suggest that query-based features, along with the content of SERPs, are effective in detecting query intent. Factors such as query category, the rank of an ad, and the total number of ads displayed on a result page relate to the context of the ad, rather than its content. We demonstrate that these context-related factors can have a major influence on expected clickthrough rate, suggesting that these factors should be taken into consideration when the performance of an ad is evaluated.     

SIMULTANEOUS STATE ESTIMATION AND LEARNING IN REPEATED COURNOT GAMES

The aim of this article is to propose that an intelligent agent can be able to decide properly in an incomplete information repeated Cournot game. The market model and the competitors’ decision models are not known to the players. The proposed agent employs a combination of the k-nearest neighbor (KNN) method and the Bayes classifier to predict the next action of its rivals, using the market decision history. The agent takes the predicted actions as an estimate of its next state and learns the expected payoff of its state-action pairs interactively using the reinforcement learning (RL) algorithm. The results of the proposed agent's competition with two benchmark competitors in different simulated Cournot games are presented. The simulation results show that the proposed agent can significantly earn more payoffs in comparison with the two benchmark agents.     

Introduction of an empirical classification system for evaluating tunneling impact on the discharge of springs (TIS) in the surrounding areas

Bulletin of Engineering Geology and the Environment - Water inflow caused by tunneling can have severe impacts on the springs’ discharge rate. If these impacts have not been predicted...     

Fish oil microencapsulation as influenced by spray dryer operational variables

The effects of spray‐drying air temperature, aspirator rate (drying air mass flow rate), peristaltic pump rate (feed mass flow rate) and spraying air mass flow rate on microencapsulation properties of fish oil including moisture content, particle size, bulk density, encapsulation efficiency and peroxide were investigated. The process was carried out on a mini spray dryer, and skim milk powder was used as the encapsulating wall material. Results indicated that increasing inlet air temperature increased the particle size, encapsulation efficiency and peroxide value but decreased the bulk density and moisture content of product. Increasing aspirator rate resulted in increased particle size and peroxide value but decreased the moisture content and bulk density. Increase in feed mass flow rate increased the moisture content, particle size, bulk density and peroxide value but decreased the encapsulation efficiency of microcapsules. The encapsulation efficiency and bulk density increased with the increasing aspirator rate but moisture content, particle size and peroxide value decreased.     

Experimental investigation of the governing parameters in the electrospinning of poly(3‐hydroxybutyrate) scaffolds: Structural characteristics of the pores

We sought to determine the impact of electrospinning parameters on a trustworthy criterion that could evidently improve the maximum applicability of fibrous scaffolds for tissue regeneration. We used an image analysis technique to elucidate the web permeability index (WPI) by modeling the formation of electrospun scaffolds. Poly(3‐hydroxybutyrate) (P3HB) scaffolds were fabricated according to predetermined conditions of levels in a Taguchi orthogonal design. The material parameters were the polymer concentration, conductivity, and volatility of the solution. The processing parameters were the applied voltage and nozzle‐to‐collector distance. With a law to monitor the WPI values when the polymer concentration or the applied voltage was increased, the pore interconnectivity was decreased. The quality of the jet instability altered the pore numbers, areas, and other structural characteristics, all of which determined the scaffold porosity and aperture interconnectivity. An initial drastic increase was observed in the WPI values because of the chain entanglement phenomenon above a 6 wt % P3HB content. Although the solution mixture significantly (p < 0.05) changed the scaffold architectural characteristics as a function of the solution viscosity and surface tension, it had a minor impact on the WPI values. The solution mixture gained the third place of significance, and the distance was approved as the least important factor. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

Performance evaluation of modified rotating-jet electrospinning method by investigating the effect of collector size on the nanofibers alignment

Modified rotating-jet electrospinning method (MRJM) is a new electrospinning technique with a novel setup including two metallic concentric hollow cylinders for generating highly aligned fibers. In this report, an experimental study was carried out to evaluate the effectiveness of MRJM for generating highly aligned nanofibers. For this purpose, the effect of voltage in the range of 10–22 kV, inner collector diameter in the range of 20–50 cm, and outer collector diameter in the range of 30–60 cm, on alignment degrees of electrospun fibers were explored and the results for each set of parameters were compared with those obtained for rotating-jet electrospinning method (RJM). The obtained results indicated that the alignment degrees of electrospun fibers in MRJM were significantly higher than those of RJM. The maximum achievable alignment degree in MRJM was around 82 % that was higher than the corresponding maximum value (40 %) of RJM. Although the effect of applied voltage on the degree of alignment in MRJM was observed to be negligible, it was experimentally proved that by manipulating the outer cylinder diameter, the degree of alignment can be increased up to 20 %. To achieve a conceptual understanding of the reason for significant influence of the outer cylinder on the elecrospinning performance, a formula was derived according to the Gauss’s law in the last part of this paper that relates the electric field strength inside the region between the inner cylinder and the spinneret to the radii of inner and outer cylinders.     

Study of liquid sloshing: numerical and experimental approach

In this paper, sloshing phenomenon in a rectangular tank under a sway excitation is studied numerically and experimentally. Although considerable advances have occurred in the development of numerical and experimental techniques for studying liquid sloshing, discrepancies exist between these techniques, particularly in predicting time history of impact pressure. The aim of this paper is to study the sloshing phenomenon experimentally and numerically using the Smoothed Particle Hydrodynamics method. The algorithm is enhanced for accurately calculating impact load in sloshing flow. Experiments were conducted on a 1:30 scaled two-dimensional tank, undergoing translational motion along its longitudinal axis. Two different sloshing flows corresponding to the ratio of exciting frequency to natural frequency were studied. The numerical and experimental results are compared for both global and local parameters and show very good agreement.     

Application of the Direct Strength Method to local buckling resistance of thin-walled steel members with non-uniform elevated temperatures under axial compression

This paper assesses the applicability of the Direct Strength Method (DSM) to calculating the local buckling ultimate strength of cold-formed thin-walled (CF-TW) steel members with non-uniform elevated temperature distributions in the cross-section. The assessment was carried out by checking the DSM calculation results with numerical simulation results using the general finite element software ABAQUS which was validated against ambient and uniform elevated temperature tests on short lipped channel sections. The validated numerical model was used to generate an extensive database (372 models) of numerical results of load carry capacity of CF-TW members with different uniform and non-uniform temperature distributions in the cross-sections, under different boundary and loading conditions and with different dimensions and lengths. It was concluded that the DSM local buckling curve was directly applicable for columns with uniform temperature distributions in the cross-section. For columns with non-uniform temperature distributions, a modification to the local buckling curve was necessary and this paper has proposed a new curve.