System and method for scoring electronic messages
View Patent ↗A system and method for collecting and analyzing electronic discussion messages to categorize the message communications and the identify trends and patterns in pre-determined markets. The system comprises an electronic data discussion system wherein electronic messages are collected and analyzed according to characteristics and data inherent in the messages. The system further comprises a data store for storing the message information and results of any analyses performed. Objective data is collected by the system for use in analyzing the electronic discussion data against real-world events to facilitate trend analysis and event forecasting based on the volume, nature and content of messages posted to electronic discussion forums.
1. A system for processing message traffic from a plurality of electronic discussion forums, comprising:
a computer implemented message collector for collecting messages from the plurality of electronic discussion forums; and
means for processing the messages based one or more topics in order to track a plurality of pseudonyms, wherein the processing includes computing a relevance score for a collected message based on at least one topic;
wherein the means for processing is further adapted to compute a buzz score based on a set of messages for the at least one topic;
wherein the buzz score is computed according to the equation:
B
=
∑
i
=
1
n
(
Rel
i
·
F
i
)
,
where Rel is a computed relevance score for a message, F is a computed influence score for a poster of a message, and n is the number of messages in the set;
wherein the influence score is computed based on the equation:
F
=
a
·
∑
i
=
1
m
(
Rel
i
·
d
i
)
+
b
·
∑
i
=
1
m
(
I
i
·
d
i
)
,
wherein a and b are selectable weighting constants, Rel is the relevance of a message, I is the impact of a message, d is a decay function that reduces the impact of older messages, and wherein m is the number of messages used to compute the influence score;
the system further comprising a computer implemented report generator for generating a report on the at least one topic using at least the buzz score.
2. The system of claim 1 , wherein the decay function d is computed based on the equation:
d
=
ⅇ
(
t
m
-
t
τ
)
,
wherein t m is the date and time a given message was posted, t is the current system date and time, and τ is a configurable constant that controls the rate of decay.
3. The system of claim 2 , wherein the impact I of a message is computed according to the equation:
I
=
Pa
-
Pb
Pa
+
Pb
,
wherein Pa is the number of unique pseudonyms that post a message during time T after a message m, Pb is the number of unique pseudonyms that post a message during time T before a message m, and wherein T is the amount of time it took for p unique pseudonyms to post a message before the current message, excluding the poster of m.
4. The system of claim 2 , wherein the buzz score is computed as a relevant buzz score.
5. A system for processing message traffic from a plurality of electronic discussion forums, comprising:
a computer implemented message collector for collecting messages from the plurality of electronic discussion forums; and
means for processing the messages based on one or more topics in order to track a plurality of pseudonyms, wherein the processing includes computing a relevance score for a collected message based on at least one topic;
wherein the means for processing is further adapted to compute a buzz score based on a set of messages for the at least one topic;
wherein the buzz score measures posting activity level weighted by the relevance of the set of messages and the influence of posting pseudonyms that posted the set of messages;
wherein the means for processing is adapted to compute a relative buzz score that measures relative changes in the posting activity level;
wherein the relative buzz score is computed as a function of an average of the buzz score and a standard deviation of the buzz score;
the system further comprising a computer implemented report generator for generating a report on the at least one topic using output of the processing means so that the report at least indirectly reflects the relative buzz score.
6. The system of claim 5 , wherein the relative buzz score B s is computed according to the equation:
B
s
=
B
-
avg
(
B
)
std
(
B
)
,
wherein B is the present buzz score, avg(B) is the average of the buzz score, and std(B) is the standard deviation of the buzz score.
7. The system of claim 6 , wherein the relative buzz score is computed as a relevant relative buzz score.
8. A system for tracking message activity levels in a plurality of electronic discussion forums, comprising:
a database storing a series of topics, wherein each of the electronic discussion forums is associated with at least one topic from the series of topics;
a computer implemented message collector for collecting messages from the plurality of electronic discussion forums; and
a computer implemented message categorizer for computing relevance scores of the messages, wherein at least one relevance score is computed based on the at least one associated topic for a source forum of a collected message;
wherein at least one of the message collector and message categorizer is adapted to extract a pseudonym author of the collected message;
wherein at least one of the message collector and the message categorizer is adapted to compute an influence score for the extracted pseudonym author;
wherein at least one of the message collector and the message categorizer is adapted to compute a reputation score for the extracted pseudonym author;
wherein the reputation score is based on a plurality of influence scores for the extracted pseudonym author under multiple local pseudonyms that have been associated into a universal pseudonym;
wherein the influence score is computed based on the equation: F=
a
·
∑
i
=
1
m
(
Rel
i
·
d
i
)
+
b
·
∑
i
=
1
m
(
I
i
·
d
i
)
,
wherein a and b are selectable weighting constants, Rel is the relevance of a message, I is the impact of a message, d is a decay function that reduces the impact of older messages, and wherein m is the number of messages used to compute the influence score;
the system further comprising a computer implemented report generator for generating a report on the at least one associated topic reflecting, at least indirectly, the relevance scores and the reputation score.
9. The method of claim 8 , wherein the decay function d is computed based on the equation:
d
=
ⅇ
(
t
m
-
t
τ
)
,
wherein t m is the date and time a given message was posted, t is the current system date and time, and τ is a configurable constant that controls the rate of decay.
10. The method of claim 9 , wherein the impact I of a message is computed according to the equation:
I
=
P
a
-
P
b
P
a
+
P
b
,
wherein Pa is the number of unique pseudonyms that post a message during time T after a message m, Pb is the number of unique pseudonyms that post a message during time T before a message m, and wherein T is the amount of time it took for p unique pseudonyms to post a message before the current message, excluding the poster of m.
11. A method for processing message traffic from a plurality of electronic discussion forums, comprising the steps of:
collecting messages from the plurality of electronic discussion forums; and
processing the messages based on a series of topics in order to track a plurality of pseudonyms, wherein the processing step comprises computing a relevance score for a collected message based on at least one topic;
wherein the processing step further comprises the step of computing a buzz score based on a set of messages for the at least one topic;
wherein the buzz score measures posting activity level weighted by the relevance of the set of messages and the influence of posting pseudonyms that posted the set of messages;
wherein the means for processing is adapted to compute a relative buzz score that measures relative changes in the posting activity level;
wherein the relative buzz score is computed as a function of an average of the buzz score and a standard deviation of the buzz score;
the method further comprising the step of generating a report on, at least in part, the at least one topic, wherein a report output is based upon, at least in part, the relative buzz score.
12. The method of claim 11 , wherein the relative buzz score B s is computed according to the equation:
B
s
=
B
-
avg
(
B
)
std
(
B
)
,
wherein B is the present buzz score, avg(B) is the average of the buzz score, and std(B) is the standard deviation of the buzz score.
13. The method of claim 12 , wherein the relative buzz score is computed as a relevant relative buzz score.