IR evaluation

Question 2 :IR Evaluation

In this exercise, firstly I have to evaluate the performance of different search engines.

Primarily, I have to choose two search engines I am familiar with such as Yahoo, Google, Bing!.

Second, I need to choose a target among the groups and design two queries to search in both search engines.

The target is chosen by the last number of your student ID. For example, if your student ID ends with the number is 1, please choose target 1; if it is 0, please choose target 10.

• Target 1: obtain the unit guide of SIT771.
• Target 2: obtain the unit guide of SIT772.
• Target 3: obtain the unit guide of SIT773.
• Target 4: obtain the unit guide of SIT774.
• Target 5: obtain the price of the new Macbook.
• Target 6: obtain the price of the new iPhone.
• Target 7: obtain the price of a Lenovo Laptop.
• Target 8: obtain the install document of MongoDB.
• Target 9: obtain the manual of MongoDB.
• Target 10: obtain the operation guide of MongoDB.

Thirdly, select the first 20 results in both search engines, if they return the target, then mark them as relevant documents, otherwise, they are irrelevant. The following exercises are based on your search results.

1. List your target and designed search queries (you can use any keywords you think are related to the target). For Search Engine 1, plot the precision versus recall curves for Query 1 and Query 2, interpolated to the 11 standard recall levels. Also plot the average precision versus recall curve for Search Engine 1 (all three curves should be on a single chart).
2. For Search Engine 2, plot the precision versus recall curves for Query 1 and Query 2, interpolated to the 11 standard recall levels. Also plot the average precision versus recall curve for Search Engine 2 (all three curves should be on a single chart, but a separate chart from that used in part (a)).
3. Plot the averages for Search Engine 1 and Search Engine 2 on a separate chart, and compare the algorithms in terms of precision and recall. Which search engine do you think is superior? Why?

SOLUTION:

Search Engines: Google/Bing

• Target 5: obtain the price of the new Macbook.

Query 1 on Google search engine: Price+New+Macbook

Precision versus recall curves for Query 1 and interpolated to the 11 standard recall levels

Actual Recall & Precision Table						Interpolated Recall & Precision Table
Rank	Relevant	N	Precision	Recall		Precision	Recall
1	R	1	1.00	0.10		1	0.0
2	R	2	1.00	0.20		1	0.1
3		2	0.67	0.20		1	0.2
4		2	0.50	0.20		0.71	0.3
5	R	3	0.60	0.30		0.71	0.4
6	R	4	0.67	0.40		0.71	0.5
7	R	5	0.71	0.50		0.67	0.6
8		5	0.63	0.50		0.64	0.7
9	R	6	0.67	0.60		0.64	0.8
10		6	0.60	0.60		0.64	0.9
11	R	7	0.64	0.70		0.56	1.0
12		7	0.58	0.70
13	R	8	0.62	0.80
14	R	8	0.64	0.80
15		8	0.60	0.80
16		8	0.56	0.80
17		8	0.53	0.80
18	R	9	0.56	0.90
19		9	0.53	0.90
20		9	0.50	0.90

Query 2 on Google search engine: MacBook + Price

Precision versus recall curves for Query 2 andinterpolated to the 11 standard recall levels

Actual Recall & Precision Table					Interpolated Recall & Precision Table:
Rank	Relevant	N	Precision	Recall	Precision	Recall
1	R	1	1.00	0.08	1	0.0
2	1	0.50	0.08	0.82	0.1
3	1	0.33	0.08	0.82	0.2
4	R	2	0.50	0.17	0.82	0.3
5	R	3	0.60	0.25	0.82	0.4
6	R	4	0.67	0.33	0.82	0.5
7	R	5	0.71	0.42	0.82	0.6
8	R	6	0.75	0.50	0.82	0.7
9	R	7	0.78	0.58	0.77	0.8
10	R	8	0.80	0.67	0.69	0.9
11	R	9	0.82	0.75	0.6	1.0
12	9	0.75	0.75
13	R	10	0.77	0.83
14	10	0.71	0.83
15	10	0.67	0.83
16	R	11	0.69	0.92
17	11	0.65	0.92
18	11	0.61	0.92
19	11	0.58	0.92
20	R	12	0.60	1.00

Average on Google search engine

Interpolated Recall & Precision Table:
Precision	Recall	Precision Query 1	Precision Query 2	Average Precision
1	0.0	1	1	1
0.82	0.1	1	0.82	0.91
0.82	0.2	1	0.82	0.91
0.82	0.3	0.71	0.82	0.77
0.82	0.4	0.71	0.82	0.77
0.82	0.5	0.71	0.82	0.77
0.82	0.6	0.67	0.82	0.75
0.82	0.7	0.64	0.82	0.73
0.77	0.8	0.64	0.77	0.71
0.69	0.9	0.64	0.69	0.67
0.6	1.0	0.56	0.6	0.58

Average precision versus recall curve for Search Engine 1 i.e. Google Search engine

Query 1 on BING search engine: Price New Macbook

Precision versus recall curves for Query 1 andinterpolated to the 11 standard recall levels

Actual Recall & Precision Table					Interpolated Recall & Precision Table:
Rank	Relevant	#	Precision	Recall	Precision	Recall
1	R	1	1.00	0.11	1	0.0
2	1	0.50	0.11	1	0.1
3	R	2	0.67	0.22	0.75	0.2
4	R	3	0.75	0.33	0.75	0.3
5	3	0.60	0.33	0.57	0.4
6	3	0.50	0.33	0.56	0.5
7	R	4	0.57	0.44	0.5	0.6
8	4	0.50	0.44	0.5	0.7
9	R	5	0.56	0.56	0.5	0.8
10	5	0.50	0.56	0.5	0.9
11	5	0.45	0.56	0.5	1.0
12	5	0.42	0.56
13	R	6	0.46	0.67
14	6	0.43	0.67
15	R	7	0.47	0.78
16	7	0.44	0.78
17	R	8	0.47	0.89
18	R	9	0.50	1.00
19	9	0.47	1.00
20	9	0.45	1.00

Query 2 on BING search engine: Macbook Price

Precision versus recall curves for Query 2 andinterpolated to the 11 standard recall levels

Actual Recall & Precision Table					Interpolated Recall & Precision Table:
Rank	Relevant	N	Precision	Recall	Precision	Recall
1	R	1	1.00	0.08	1	0.0
2	1	0.50	0.08	0.67	0.1
3	1	0.33	0.08	0.67	0.2
4	1	0.25	0.08	0.67	0.3
5	1	0.20	0.08	0.67	0.4
6	R	2	0.33	0.17	0.67	0.5
7	R	3	0.43	0.25	0.67	0.6
8	R	4	0.50	0.33	0.67	0.7
9	R	5	0.56	0.42	0.67	0.8
10	R	6	0.60	0.50	0.63	0.9
11	R	7	0.64	0.58	0.63	1.0
12	7	0.58	0.58
13	R	8	0.62	0.67
14	R	9	0.64	0.75
15	R	10	0.67	0.83
16	10	0.63	0.83
17	10	0.59	0.83
18	R	11	0.61	0.92
19	R	12	0.63	1.00
20	12	0.60	1.00

Average on Bing search engine

Average precision versus recall curve for Search Engine 2 i.e. Bing search engine

Interpolated Recall & Precision Table:
Precision	Recall	Precision Query 1	Precision Query 2	Average Precision
1	0.0	1	1	1
0.82	0.1	1	0.67	0.84
0.82	0.2	0.75	0.67	0.71
0.82	0.3	0.75	0.67	0.71
0.82	0.4	0.57	0.67	0.62
0.82	0.5	0.56	0.67	0.62
0.82	0.6	0.5	0.67	0.59
0.82	0.7	0.5	0.67	0.59
0.77	0.8	0.5	0.67	0.59
0.69	0.9	0.5	0.63	0.57
0.6	1.0	0.5	0.63	0.57

Buy IR evaluation Assignment Answers Online

Talk to our expert to get the help with IR evaluation Assignment to complete your assessment on time and boost your grades now

The main aim/motive of the management assignment help services is to get connect with a greater number of students, and effectively help, and support them in getting completing their assignments the students also get find this a wonderful opportunity where they could effectively learn more about their topics, as the experts also have the best team members with them in which all the members effectively support each other to get complete their diploma assignments. They complete the assessments of the students in an appropriate manner and deliver them back to the students before the due date of the assignment so that the students could timely submit this, and can score higher marks. The experts of the assignment help services at urgenthomework.com are so much skilled, capable, talented, and experienced in their field of programming homework help writing assignments, so, for this, they can effectively write the best economics assignment help services.

Get Online Support for IR evaluation Assignment Assignment Help Online